agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH v4] Add pg_tablespace_avail() functions 102+ messages / 2 participants [nested] [flat]
* [PATCH v4] Add pg_tablespace_avail() functions @ 2025-03-14 15:29 Christoph Berg <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Christoph Berg @ 2025-03-14 15:29 UTC (permalink / raw) This exposes the f_avail value from statvfs() on tablespace directories on the SQL level, allowing monitoring of free disk space from within the server. On windows, GetDiskFreeSpaceEx() is used. Permissions required match those from pg_tablespace_size(). In psql, include a new "Free" column in \db+ output. Add test coverage for pg_tablespace_avail() and the previously not covered pg_tablespace_size() function. --- doc/src/sgml/func.sgml | 21 +++++ doc/src/sgml/ref/psql-ref.sgml | 2 +- src/backend/utils/adt/dbsize.c | 102 +++++++++++++++++++++++ src/bin/psql/describe.c | 11 ++- src/include/catalog/pg_proc.dat | 8 ++ src/test/regress/expected/tablespace.out | 21 +++++ src/test/regress/sql/tablespace.sql | 10 +++ 7 files changed, 171 insertions(+), 4 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index 51dd8ad6571..0b4456ad958 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -30093,6 +30093,27 @@ postgres=# SELECT '0/0'::pg_lsn + pd.segment_number * ps.setting::int + :offset </para></entry> </row> + <row> + <entry role="func_table_entry"><para role="func_signature"> + <indexterm> + <primary>pg_tablespace_avail</primary> + </indexterm> + <function>pg_tablespace_avail</function> ( <type>name</type> ) + <returnvalue>bigint</returnvalue> + </para> + <para role="func_signature"> + <function>pg_tablespace_avail</function> ( <type>oid</type> ) + <returnvalue>bigint</returnvalue> + </para> + <para> + Returns the available disk space in the tablespace with the + specified name or OID. To use this function, you must + have <literal>CREATE</literal> privilege on the specified tablespace + or have privileges of the <literal>pg_read_all_stats</literal> role, + unless it is the default tablespace for the current database. + </para></entry> + </row> + <row> <entry role="func_table_entry"><para role="func_signature"> <indexterm> diff --git a/doc/src/sgml/ref/psql-ref.sgml b/doc/src/sgml/ref/psql-ref.sgml index cedccc14129..9e1bec0b422 100644 --- a/doc/src/sgml/ref/psql-ref.sgml +++ b/doc/src/sgml/ref/psql-ref.sgml @@ -1492,7 +1492,7 @@ SELECT $1 \parse stmt1 If <literal>x</literal> is appended to the command name, the results are displayed in expanded mode. If <literal>+</literal> is appended to the command name, each tablespace - is listed with its associated options, on-disk size, permissions and + is listed with its associated options, on-disk size and free disk space, permissions and description. </para> </listitem> diff --git a/src/backend/utils/adt/dbsize.c b/src/backend/utils/adt/dbsize.c index 25865b660ef..9bd8667c2d9 100644 --- a/src/backend/utils/adt/dbsize.c +++ b/src/backend/utils/adt/dbsize.c @@ -12,6 +12,12 @@ #include "postgres.h" #include <sys/stat.h> +#ifdef WIN32 +#include <fileapi.h> +#include <errhandlingapi.h> +#else +#include <sys/statvfs.h> +#endif #include "access/htup_details.h" #include "access/relation.h" @@ -316,6 +322,102 @@ pg_tablespace_size_name(PG_FUNCTION_ARGS) } +/* + * Return available disk space of tablespace. Returns -1 if the tablespace + * directory cannot be found. + */ +static int64 +calculate_tablespace_avail(Oid tblspcOid) +{ + char tblspcPath[MAXPGPATH]; + AclResult aclresult; +#ifdef WIN32 + ULARGE_INTEGER lpFreeBytesAvailable; +#else + struct statvfs fst; +#endif + + /* + * User must have privileges of pg_read_all_stats or have CREATE privilege + * for target tablespace, either explicitly granted or implicitly because + * it is default for current database. + */ + if (tblspcOid != MyDatabaseTableSpace && + !has_privs_of_role(GetUserId(), ROLE_PG_READ_ALL_STATS)) + { + aclresult = object_aclcheck(TableSpaceRelationId, tblspcOid, GetUserId(), ACL_CREATE); + if (aclresult != ACLCHECK_OK) + aclcheck_error(aclresult, OBJECT_TABLESPACE, + get_tablespace_name(tblspcOid)); + } + + if (tblspcOid == DEFAULTTABLESPACE_OID) + snprintf(tblspcPath, MAXPGPATH, "base"); + else if (tblspcOid == GLOBALTABLESPACE_OID) + snprintf(tblspcPath, MAXPGPATH, "global"); + else + snprintf(tblspcPath, MAXPGPATH, "%s/%u/%s", PG_TBLSPC_DIR, tblspcOid, + TABLESPACE_VERSION_DIRECTORY); + +#ifdef WIN32 + if (! GetDiskFreeSpaceEx(tblspcPath, &lpFreeBytesAvailable, NULL, NULL)) + elog(ERROR, "GetDiskFreeSpaceEx failed: error code %lu", GetLastError()); + + return lpFreeBytesAvailable.QuadPart; /* ULONGLONG part of ULARGE_INTEGER */ +#else + if (statvfs(tblspcPath, &fst) < 0) + { + if (errno == ENOENT) + return -1; + else + ereport(ERROR, + (errcode_for_file_access(), + errmsg("could not statvfs directory \"%s\": %m", tblspcPath))); + } + + return fst.f_bavail * fst.f_frsize; /* available blocks times fragment size */ +#endif +} + +Datum +pg_tablespace_avail_oid(PG_FUNCTION_ARGS) +{ + Oid tblspcOid = PG_GETARG_OID(0); + int64 avail; + + /* + * Not needed for correctness, but avoid non-user-facing error message + * later if the tablespace doesn't exist. + */ + if (!SearchSysCacheExists1(TABLESPACEOID, ObjectIdGetDatum(tblspcOid))) + ereport(ERROR, + errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("tablespace with OID %u does not exist", tblspcOid)); + + avail = calculate_tablespace_avail(tblspcOid); + + if (avail < 0) + PG_RETURN_NULL(); + + PG_RETURN_INT64(avail); +} + +Datum +pg_tablespace_avail_name(PG_FUNCTION_ARGS) +{ + Name tblspcName = PG_GETARG_NAME(0); + Oid tblspcOid = get_tablespace_oid(NameStr(*tblspcName), false); + int64 avail; + + avail = calculate_tablespace_avail(tblspcOid); + + if (avail < 0) + PG_RETURN_NULL(); + + PG_RETURN_INT64(avail); +} + + /* * calculate size of (one fork of) a relation * diff --git a/src/bin/psql/describe.c b/src/bin/psql/describe.c index e6cf468ac9e..8c52a126ac1 100644 --- a/src/bin/psql/describe.c +++ b/src/bin/psql/describe.c @@ -241,10 +241,15 @@ describeTablespaces(const char *pattern, bool verbose) printACLColumn(&buf, "spcacl"); appendPQExpBuffer(&buf, ",\n spcoptions AS \"%s\"" - ",\n pg_catalog.pg_size_pretty(pg_catalog.pg_tablespace_size(oid)) AS \"%s\"" - ",\n pg_catalog.shobj_description(oid, 'pg_tablespace') AS \"%s\"", + ",\n pg_catalog.pg_size_pretty(pg_catalog.pg_tablespace_size(oid)) AS \"%s\"", gettext_noop("Options"), - gettext_noop("Size"), + gettext_noop("Size")); + if (pset.sversion >= 180000) + appendPQExpBuffer(&buf, + ",\n pg_catalog.pg_size_pretty(pg_catalog.pg_tablespace_avail(oid)) AS \"%s\"", + gettext_noop("Free")); + appendPQExpBuffer(&buf, + ",\n pg_catalog.shobj_description(oid, 'pg_tablespace') AS \"%s\"", gettext_noop("Description")); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 42e427f8fe8..9d64da6bfb8 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -7680,6 +7680,14 @@ descr => 'total disk space usage for the specified tablespace', proname => 'pg_tablespace_size', provolatile => 'v', prorettype => 'int8', proargtypes => 'name', prosrc => 'pg_tablespace_size_name' }, +{ oid => '6015', + descr => 'disk stats for the specified tablespace', + proname => 'pg_tablespace_avail', provolatile => 'v', prorettype => 'int8', + proargtypes => 'oid', prosrc => 'pg_tablespace_avail_oid' }, +{ oid => '6016', + descr => 'disk stats for the specified tablespace', + proname => 'pg_tablespace_avail', provolatile => 'v', prorettype => 'int8', + proargtypes => 'name', prosrc => 'pg_tablespace_avail_name' }, { oid => '2324', descr => 'total disk space usage for the specified database', proname => 'pg_database_size', provolatile => 'v', prorettype => 'int8', proargtypes => 'oid', prosrc => 'pg_database_size_oid' }, diff --git a/src/test/regress/expected/tablespace.out b/src/test/regress/expected/tablespace.out index a90e39e5738..6709ed794df 100644 --- a/src/test/regress/expected/tablespace.out +++ b/src/test/regress/expected/tablespace.out @@ -20,6 +20,27 @@ SELECT spcoptions FROM pg_tablespace WHERE spcname = 'regress_tblspacewith'; {random_page_cost=3.0} (1 row) +-- check size functions +SELECT pg_tablespace_size('pg_default') BETWEEN 1_000_000 and 10_000_000_000, -- rough sanity check + pg_tablespace_size('pg_global') BETWEEN 100_000 and 10_000_000, + pg_tablespace_size('regress_tblspacewith'); -- empty + ?column? | ?column? | pg_tablespace_size +----------+----------+-------------------- + t | t | 0 +(1 row) + +SELECT pg_tablespace_size('missing'); +ERROR: tablespace "missing" does not exist +SELECT pg_tablespace_avail('pg_default') > 1_000_000, + pg_tablespace_avail('pg_global') > 1_000_000, + pg_tablespace_avail('regress_tblspacewith') > 1_000_000; + ?column? | ?column? | ?column? +----------+----------+---------- + t | t | t +(1 row) + +SELECT pg_tablespace_avail('missing'); +ERROR: tablespace "missing" does not exist -- drop the tablespace so we can re-use the location DROP TABLESPACE regress_tblspacewith; -- This returns a relative path as of an effect of allow_in_place_tablespaces, diff --git a/src/test/regress/sql/tablespace.sql b/src/test/regress/sql/tablespace.sql index dfe3db096e2..3fcd4bb00ff 100644 --- a/src/test/regress/sql/tablespace.sql +++ b/src/test/regress/sql/tablespace.sql @@ -17,6 +17,16 @@ CREATE TABLESPACE regress_tblspacewith LOCATION '' WITH (random_page_cost = 3.0) -- check to see the parameter was used SELECT spcoptions FROM pg_tablespace WHERE spcname = 'regress_tblspacewith'; +-- check size functions +SELECT pg_tablespace_size('pg_default') BETWEEN 1_000_000 and 10_000_000_000, -- rough sanity check + pg_tablespace_size('pg_global') BETWEEN 100_000 and 10_000_000, + pg_tablespace_size('regress_tblspacewith'); -- empty +SELECT pg_tablespace_size('missing'); +SELECT pg_tablespace_avail('pg_default') > 1_000_000, + pg_tablespace_avail('pg_global') > 1_000_000, + pg_tablespace_avail('regress_tblspacewith') > 1_000_000; +SELECT pg_tablespace_avail('missing'); + -- drop the tablespace so we can re-use the location DROP TABLESPACE regress_tblspacewith; -- 2.47.2 --mxigUiQ2jY+Id+Rf-- ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 221 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 160 insertions(+), 110 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index fa98b8b9247..04d39ad8c86 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -93,40 +93,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -173,22 +139,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -197,6 +160,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2613,18 +2579,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2633,7 +2612,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2682,14 +2661,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2705,7 +2684,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2718,7 +2697,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2726,7 +2705,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2735,6 +2714,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2742,16 +2723,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2763,10 +2743,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2794,8 +2774,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2944,10 +2924,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2958,9 +2939,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2968,13 +2949,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -2997,16 +2978,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3077,7 +3058,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3093,41 +3074,65 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); - chgcxt->cc_rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); - InitResultRelInfo(chgcxt->cc_rri, relation, 0, 0, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = (ResultRelInfo *) palloc(sizeof(ResultRelInfo)); + InitResultRelInfo(dest->rri, relation, 0, 0, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3137,12 +3142,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3161,34 +3166,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f9eb23e52c9..b4d5abbaca7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2660,6 +2660,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
* [PATCH 3/8] Introduce RepackDest structure. @ 2026-07-15 08:37 Antonin Houska <[email protected]> 0 siblings, 0 replies; 102+ messages in thread From: Antonin Houska @ 2026-07-15 08:37 UTC (permalink / raw) This is for ChangeContext to handle insertions into two relations: besides the new relation (whose file will eventually be used by the REPACKed relation), an "auxiliary relation" is needed sometimes, in order to get the data sorted. The concept is introduced and explained later in the patch series. --- src/backend/commands/repack.c | 223 ++++++++++++++++--------------- src/include/commands/repack.h | 48 +++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 161 insertions(+), 111 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 19927c15bf3..392332b4b2b 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -95,40 +95,6 @@ typedef struct Oid indexOid; } RelToCluster; -/* - * 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. - */ -typedef struct ChangeContext -{ - /* The relation the changes are applied to. */ - Relation cc_rel; - - /* Needed to update indexes of cc_rel. */ - ResultRelInfo *cc_rri; - EState *cc_estate; - - /* - * Existing tuples to UPDATE and DELETE are located via this index. We - * keep the scankey in partially initialized state to avoid repeated work. - * sk_argument is completed on the fly. - */ - Relation cc_ident_index; - ScanKey cc_ident_key; - int cc_ident_key_nentries; - - /* The latest column we need to deform to have the tuple identity */ - AttrNumber cc_last_key_attno; - - /* Sequential number of the file containing the changes. */ - int cc_file_seq; -} ChangeContext; - /* * Backend-local information to control the decoding worker. */ @@ -175,22 +141,19 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool repack_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt); -static void apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt); -static void apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt); +static void apply_concurrent_changes(ChangeContext *chgcxt); +static void apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot); +static void apply_concurrent_update(RepackDest *dest, + TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple); static void apply_concurrent_delete(Relation rel, TupleTableSlot *slot); static void restore_tuple(BufFile *file, Relation relation, TupleTableSlot *slot); static void adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *src); -static bool find_target_tuple(Relation rel, ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved); -static bool identity_key_equal(ChangeContext *chgcxt, - TupleTableSlot *locator, +static bool identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate); static void process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, @@ -199,6 +162,9 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id); static void release_change_context(ChangeContext *chgcxt); +static void initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id); +static void release_change_dest(RepackDest *dest); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Oid identIdx, TransactionId frozenXid, @@ -2614,18 +2580,31 @@ RepackCommandAsString(RepackCommand cmd) } /* - * Apply all the changes stored in 'file'. + * Apply all the changes provided by decoding worker. */ static void -apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) +apply_concurrent_changes(ChangeContext *chgcxt) { ConcurrentChangeKind kind = '\0'; - Relation rel = chgcxt->cc_rel; + RepackDest *dest; + Relation rel; TupleTableSlot *spilled_tuple; TupleTableSlot *old_update_tuple; TupleTableSlot *ondisk_tuple; bool have_old_tuple = false; MemoryContext oldcxt; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + + dest = &chgcxt->cc_dest; + rel = dest->rel; + + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + + /* Open the file containing the changes. */ + DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); @@ -2634,7 +2613,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel), &TTSOpsVirtual); - oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate)); + oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(dest->estate)); while (true) { @@ -2683,14 +2662,14 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) if (kind == CHANGE_INSERT) { - apply_concurrent_insert(rel, spilled_tuple, chgcxt); + apply_concurrent_insert(dest, spilled_tuple); } else if (kind == CHANGE_DELETE) { bool found; /* Find the tuple to be deleted */ - found = find_target_tuple(rel, chgcxt, spilled_tuple, ondisk_tuple); + found = find_target_tuple(dest, spilled_tuple, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); apply_concurrent_delete(rel, ondisk_tuple); @@ -2706,7 +2685,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) key = spilled_tuple; /* Find the tuple to be updated or deleted. */ - found = find_target_tuple(rel, chgcxt, key, ondisk_tuple); + found = find_target_tuple(dest, key, ondisk_tuple); if (!found) elog(ERROR, "could not find target tuple"); @@ -2719,7 +2698,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) */ adjust_toast_pointers(rel, spilled_tuple, ondisk_tuple); - apply_concurrent_update(rel, spilled_tuple, ondisk_tuple, chgcxt); + apply_concurrent_update(dest, spilled_tuple, ondisk_tuple); ExecClearTuple(old_update_tuple); have_old_tuple = false; @@ -2727,7 +2706,7 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) else elog(ERROR, "unrecognized kind of change: %d", kind); - ResetPerTupleExprContext(chgcxt->cc_estate); + ResetPerTupleExprContext(dest->estate); } /* Cleanup. */ @@ -2736,6 +2715,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) ExecDropSingleTupleTableSlot(old_update_tuple); MemoryContextSwitchTo(oldcxt); + + BufFileClose(file); } /* @@ -2743,16 +2724,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt) * table. */ static void -apply_concurrent_insert(Relation rel, TupleTableSlot *slot, - ChangeContext *chgcxt) +apply_concurrent_insert(RepackDest *dest, TupleTableSlot *slot) { /* Put the tuple in the table, but make sure it won't be decoded */ - table_tuple_insert(rel, slot, GetCurrentCommandId(true), + table_tuple_insert(dest->rel, slot, GetCurrentCommandId(true), TABLE_INSERT_NO_LOGICAL, NULL); /* Update indexes with this new tuple. */ - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, 0, slot, NIL, NULL); @@ -2764,10 +2744,10 @@ apply_concurrent_insert(Relation rel, TupleTableSlot *slot, * table. */ static void -apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, - TupleTableSlot *ondisk_tuple, - ChangeContext *chgcxt) +apply_concurrent_update(RepackDest *dest, TupleTableSlot *spilled_tuple, + TupleTableSlot *ondisk_tuple) { + Relation rel = dest->rel; LockTupleMode lockmode; TM_FailureData tmfd; TU_UpdateIndexes update_indexes; @@ -2795,8 +2775,8 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple, if (update_indexes == TU_Summarizing) flags |= EIIT_ONLY_SUMMARIZING; - ExecInsertIndexTuples(chgcxt->cc_rri, - chgcxt->cc_estate, + ExecInsertIndexTuples(dest->rri, + dest->estate, flags, spilled_tuple, NIL, NULL); @@ -2948,10 +2928,11 @@ adjust_toast_pointers(Relation relation, TupleTableSlot *dest, TupleTableSlot *s * not found, return false. */ static bool -find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, +find_target_tuple(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *retrieved) { - Form_pg_index idx = chgcxt->cc_ident_index->rd_index; + Relation rel = dest->rel; + Form_pg_index idx = dest->ident_index->rd_index; IndexScanDesc scan; bool retval = false; @@ -2962,9 +2943,9 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * * Use the incoming tuple to finalize the scan key. */ - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; + ScanKey entry = &dest->ident_key[i]; AttrNumber attno = idx->indkey.values[i]; entry->sk_argument = locator->tts_values[attno - 1]; @@ -2972,13 +2953,13 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, } /* XXX no instrumentation for now */ - scan = index_beginscan(rel, chgcxt->cc_ident_index, GetActiveSnapshot(), - NULL, chgcxt->cc_ident_key_nentries, 0, 0); - index_rescan(scan, chgcxt->cc_ident_key, chgcxt->cc_ident_key_nentries, NULL, 0); + scan = index_beginscan(rel, dest->ident_index, GetActiveSnapshot(), + NULL, dest->ident_key_nentries, 0, 0); + index_rescan(scan, dest->ident_key, dest->ident_key_nentries, NULL, 0); while (index_getnext_slot(scan, ForwardScanDirection, retrieved)) { /* Be wary of temporal constraints */ - if (scan->xs_recheck && !identity_key_equal(chgcxt, locator, retrieved)) + if (scan->xs_recheck && !identity_key_equal(dest, locator, retrieved)) { CHECK_FOR_INTERRUPTS(); continue; @@ -3001,16 +2982,16 @@ find_target_tuple(Relation rel, ChangeContext *chgcxt, TupleTableSlot *locator, * used for temporal constraints. */ static bool -identity_key_equal(ChangeContext *chgcxt, TupleTableSlot *locator, +identity_key_equal(RepackDest *dest, TupleTableSlot *locator, TupleTableSlot *candidate) { - slot_getsomeattrs(locator, chgcxt->cc_last_key_attno); - slot_getsomeattrs(candidate, chgcxt->cc_last_key_attno); + slot_getsomeattrs(locator, dest->last_key_attno); + slot_getsomeattrs(candidate, dest->last_key_attno); - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + for (int i = 0; i < dest->ident_key_nentries; i++) { - ScanKey entry = &chgcxt->cc_ident_key[i]; - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + ScanKey entry = &dest->ident_key[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); @@ -3081,7 +3062,7 @@ process_concurrent_changes(XLogRecPtr end_of_wal, ChangeContext *chgcxt, bool do /* Open the file. */ DecodingWorkerFileName(fname, shared->relid, chgcxt->cc_file_seq); file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); - apply_concurrent_changes(file, chgcxt); + apply_concurrent_changes(chgcxt); BufFileClose(file); @@ -3097,10 +3078,34 @@ static void initialize_change_context(ChangeContext *chgcxt, Relation relation, Oid ident_index_id) { - chgcxt->cc_rel = relation; + initialize_change_dest(&chgcxt->cc_dest, relation, ident_index_id); + + chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; +} + +/* + * Free up resources taken by a ChangeContext. + */ +static void +release_change_context(ChangeContext *chgcxt) +{ + release_change_dest(&chgcxt->cc_dest); +} + +/* + * Initialize the RepackDest struct for the given relation, with the given + * index as identity index. InvalidOid can be specified to only make the + * relation ready for insertions. + */ +static void +initialize_change_dest(RepackDest *dest, Relation relation, + Oid ident_index_id) +{ + dest->rel = relation; + dest->bistate = GetBulkInsertState(); /* Only initialize fields needed by ExecInsertIndexTuples(). */ - chgcxt->cc_estate = CreateExecutorState(); + dest->estate = CreateExecutorState(); /* * Set up a range table for the executor, containing our repacked table as @@ -3149,41 +3154,41 @@ initialize_change_context(ChangeContext *chgcxt, perminfo->updatedCols = updatedCols; /* finally we can initialize the range table proper */ - ExecInitRangeTable(chgcxt->cc_estate, list_make1(rte), perminfos, + ExecInitRangeTable(dest->estate, list_make1(rte), perminfos, bms_make_singleton(1)); } /* Set up our ResultRelInfo to use for index updates */ - chgcxt->cc_rri = makeNode(ResultRelInfo); - InitResultRelInfo(chgcxt->cc_rri, relation, 1, NULL, 0); - ExecOpenIndices(chgcxt->cc_rri, false); + dest->rri = makeNode(ResultRelInfo); + InitResultRelInfo(dest->rri, relation, 1, NULL, 0); + ExecOpenIndices(dest->rri, false); /* * The table's relcache entry already has the relcache entry for the * identity index; find that. */ - chgcxt->cc_ident_index = NULL; - for (int i = 0; i < chgcxt->cc_rri->ri_NumIndices; i++) + dest->ident_index = NULL; + for (int i = 0; i < dest->rri->ri_NumIndices; i++) { Relation ind_rel; - ind_rel = chgcxt->cc_rri->ri_IndexRelationDescs[i]; + ind_rel = dest->rri->ri_IndexRelationDescs[i]; if (ind_rel->rd_id == ident_index_id) { - chgcxt->cc_ident_index = ind_rel; + dest->ident_index = ind_rel; break; } } - if (chgcxt->cc_ident_index == NULL) + if (dest->ident_index == NULL) elog(ERROR, "could not find identity index"); /* Set up for scanning said identity index */ { Form_pg_index indexForm; - indexForm = chgcxt->cc_ident_index->rd_index; - chgcxt->cc_ident_key_nentries = indexForm->indnkeyatts; - chgcxt->cc_ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); + indexForm = dest->ident_index->rd_index; + dest->ident_key_nentries = indexForm->indnkeyatts; + dest->ident_key = (ScanKey) palloc_array(ScanKeyData, indexForm->indnkeyatts); for (int i = 0; i < indexForm->indnkeyatts; i++) { ScanKey entry; @@ -3193,12 +3198,12 @@ initialize_change_context(ChangeContext *chgcxt, opcode; StrategyNumber eq_strategy; - entry = &chgcxt->cc_ident_key[i]; + entry = &dest->ident_key[i]; - opfamily = chgcxt->cc_ident_index->rd_opfamily[i]; - opcintype = chgcxt->cc_ident_index->rd_opcintype[i]; + opfamily = dest->ident_index->rd_opfamily[i]; + opcintype = dest->ident_index->rd_opcintype[i]; eq_strategy = IndexAmTranslateCompareType(COMPARE_EQ, - chgcxt->cc_ident_index->rd_rel->relam, + dest->ident_index->rd_rel->relam, opfamily, false); if (eq_strategy == InvalidStrategy) elog(ERROR, "could not find equality strategy for index operator family %u for type %u", @@ -3217,34 +3222,30 @@ initialize_change_context(ChangeContext *chgcxt, i + 1, eq_strategy, opcode, (Datum) 0); - entry->sk_collation = chgcxt->cc_ident_index->rd_indcollation[i]; + entry->sk_collation = dest->ident_index->rd_indcollation[i]; } } /* Determine the last column we must deform to read the identity */ - chgcxt->cc_last_key_attno = InvalidAttrNumber; - for (int i = 0; i < chgcxt->cc_ident_key_nentries; i++) + dest->last_key_attno = InvalidAttrNumber; + for (int i = 0; i < dest->ident_key_nentries; i++) { - AttrNumber attno = chgcxt->cc_ident_index->rd_index->indkey.values[i]; + AttrNumber attno = dest->ident_index->rd_index->indkey.values[i]; Assert(attno > 0); - chgcxt->cc_last_key_attno = Max(chgcxt->cc_last_key_attno, attno); + dest->last_key_attno = Max(dest->last_key_attno, attno); } - - chgcxt->cc_file_seq = WORKER_FILE_SNAPSHOT + 1; } -/* - * Free up resources taken by a ChangeContext. - */ static void -release_change_context(ChangeContext *chgcxt) +release_change_dest(RepackDest *dest) { - ExecCloseIndices(chgcxt->cc_rri); - FreeExecutorState(chgcxt->cc_estate); + FreeBulkInsertState(dest->bistate); + ExecCloseIndices(dest->rri); + FreeExecutorState(dest->estate); /* XXX are these pfrees necessary? */ - pfree(chgcxt->cc_rri); - pfree(chgcxt->cc_ident_key); + pfree(dest->rri); + pfree(dest->ident_key); } /* diff --git a/src/include/commands/repack.h b/src/include/commands/repack.h index 27105c10591..07f887e99f6 100644 --- a/src/include/commands/repack.h +++ b/src/include/commands/repack.h @@ -16,6 +16,7 @@ #include <signal.h> #include "access/hio.h" +#include "access/skey.h" #include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "parser/parse_node.h" @@ -39,6 +40,53 @@ typedef struct ClusterParams extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; +/* + * Table to apply concurrent data changes to. + */ +typedef struct RepackDest +{ + /* The relation the changes are applied to. */ + Relation rel; + + BulkInsertStateData *bistate; + + /* Needed to update indexes of cc_rel. */ + ResultRelInfo *rri; + EState *estate; + + /* + * Existing tuples to UPDATE and DELETE are located via this index. We + * keep the scankey in partially initialized state to avoid repeated work. + * sk_argument is completed on the fly. + */ + Relation ident_index; + ScanKey ident_key; + + int ident_key_nentries; + + /* The latest column we need to deform to have the tuple identity */ + AttrNumber last_key_attno; +} RepackDest; + +/* + * 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. + * + * XXX Now that it's in *.h file, rename to RepackChangeContext? + */ +typedef struct ChangeContext +{ + /* The destination table. */ + RepackDest cc_dest; + + /* Sequential number of the file containing the changes. */ + int cc_file_seq; +} ChangeContext; extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 56c1f997f88..25ac7079099 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2664,6 +2664,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepackCommand +RepackDest RepackDecodingState RepackStmt ReparameterizeForeignPathByChild_function -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v02-0004-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 102+ messages in thread
end of thread, other threads:[~2026-07-15 08:37 UTC | newest] Thread overview: 102+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2025-03-14 15:29 [PATCH v4] Add pg_tablespace_avail() functions Christoph Berg <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-06-16 11:54 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. Antonin Houska <[email protected]> 2026-07-15 08:37 [PATCH 3/8] Introduce RepackDest structure. 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