agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH] fix "Preserve relfilenodes" for pg_largeobject and its index 261+ messages / 3 participants [nested] [flat]
* [PATCH] fix "Preserve relfilenodes" for pg_largeobject and its index @ 2022-07-02 05:48 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Justin Pryzby @ 2022-07-02 05:48 UTC (permalink / raw) An empty table is created by initdb, and the filenode was still pointing to that, so pg_largeobject was empty after binary upgrades. Test like: | ./tmp_install/usr/local/pgsql/bin/initdb --no-sync -D pg15b1.dat -k | ./tmp_install/usr/local/pgsql/bin/postgres -D pg15b1.dat -c logging_collector=no -p 5678 -k /tmp& | psql -h /tmp postgres -p 5678 -c '\lo_import /etc/shells' -c 'VACUUM FULL pg_largeobject' | rm -fr pg15b2.dat && ./tmp_install/usr/local/pgsql/bin/initdb --no-sync -k -D pg15b2.dat && ./tmp_install/usr/local/pgsql/bin/pg_upgrade -d pg15b1.dat -D pg15b2.dat -b ./tmp_install/usr/local/pgsql/bin | ./tmp_install/usr/local/pgsql/bin/postgres -D pg15b2.dat -c logging_collector=no -p 5678 -k /tmp& See also: 9a974cbcba005256a19991203583a94b4f9a21a9 https://www.postgresql.org/message-id/20210601140949.GC22012%40momjian.us https://www.postgresql.org/message-id/20220701231413.GI13040%40telsasoft.com --- src/bin/pg_dump/pg_dump.c | 37 ++++++++------ src/bin/pg_upgrade/relfilenumber.c | 68 +++++++++++++++++++++++--- src/bin/pg_upgrade/t/002_pg_upgrade.pl | 2 + 3 files changed, 86 insertions(+), 21 deletions(-) diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 227cdca2e2d..06d436f2f34 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -3135,7 +3135,7 @@ dumpDatabase(Archive *fout) /* * pg_largeobject comes from the old system intact, so set its - * relfrozenxids and relminmxids. + * relfrozenxids, relminmxids and relfilenode. */ if (dopt->binary_upgrade) { @@ -3143,34 +3143,41 @@ dumpDatabase(Archive *fout) PQExpBuffer loFrozenQry = createPQExpBuffer(); PQExpBuffer loOutQry = createPQExpBuffer(); int i_relfrozenxid, + i_relfilenode, + i_oid, i_relminmxid; /* * pg_largeobject */ if (fout->remoteVersion >= 90300) - appendPQExpBuffer(loFrozenQry, "SELECT relfrozenxid, relminmxid\n" + appendPQExpBuffer(loFrozenQry, "SELECT relfrozenxid, relminmxid, relfilenode, oid\n" "FROM pg_catalog.pg_class\n" - "WHERE oid = %u;\n", - LargeObjectRelationId); + "WHERE oid IN (%u, %u);\n", + LargeObjectRelationId, LargeObjectLOidPNIndexId); else - appendPQExpBuffer(loFrozenQry, "SELECT relfrozenxid, 0 AS relminmxid\n" + appendPQExpBuffer(loFrozenQry, "SELECT relfrozenxid, 0 AS relminmxid, relfilenode, oid\n" "FROM pg_catalog.pg_class\n" - "WHERE oid = %u;\n", - LargeObjectRelationId); + "WHERE oid IN (%u, %u);\n", + LargeObjectRelationId, LargeObjectLOidPNIndexId); - lo_res = ExecuteSqlQueryForSingleRow(fout, loFrozenQry->data); + lo_res = ExecuteSqlQuery(fout, loFrozenQry->data, PGRES_TUPLES_OK); i_relfrozenxid = PQfnumber(lo_res, "relfrozenxid"); i_relminmxid = PQfnumber(lo_res, "relminmxid"); + i_relfilenode = PQfnumber(lo_res, "relfilenode"); + i_oid = PQfnumber(lo_res, "oid"); + + appendPQExpBufferStr(loOutQry, "\n-- For binary upgrade, preserve values for pg_largeobject and its index\n"); + for (int i = 0; i < PQntuples(lo_res); ++i) + appendPQExpBuffer(loOutQry, "UPDATE pg_catalog.pg_class\n" + "SET relfrozenxid = '%u', relminmxid = '%u', relfilenode = '%u'\n" + "WHERE oid = %u;\n", + atooid(PQgetvalue(lo_res, i, i_relfrozenxid)), + atooid(PQgetvalue(lo_res, i, i_relminmxid)), + atooid(PQgetvalue(lo_res, i, i_relfilenode)), + atooid(PQgetvalue(lo_res, i, i_oid))); - appendPQExpBufferStr(loOutQry, "\n-- For binary upgrade, set pg_largeobject relfrozenxid and relminmxid\n"); - appendPQExpBuffer(loOutQry, "UPDATE pg_catalog.pg_class\n" - "SET relfrozenxid = '%u', relminmxid = '%u'\n" - "WHERE oid = %u;\n", - atooid(PQgetvalue(lo_res, 0, i_relfrozenxid)), - atooid(PQgetvalue(lo_res, 0, i_relminmxid)), - LargeObjectRelationId); ArchiveEntry(fout, nilCatalogId, createDumpId(), ARCHIVE_OPTS(.tag = "pg_largeobject", .description = "pg_largeobject", diff --git a/src/bin/pg_upgrade/relfilenumber.c b/src/bin/pg_upgrade/relfilenumber.c index b3ad8209eca..0dd649aa0f5 100644 --- a/src/bin/pg_upgrade/relfilenumber.c +++ b/src/bin/pg_upgrade/relfilenumber.c @@ -13,9 +13,13 @@ #include "access/transam.h" #include "catalog/pg_class_d.h" +#include "catalog/pg_largeobject_d.h" #include "pg_upgrade.h" -static void transfer_single_new_db(FileNameMap *maps, int size, char *old_tablespace); +static void transfer_single_new_db(FileNameMap *maps, int size, char *old_tablespace, + bool *has_lotable, bool *has_loindex); +static void remove_stray_largeobject_files(DbInfo *new_db, bool has_lotable, + bool has_loindex); static void transfer_relfile(FileNameMap *map, const char *suffix, bool vm_must_add_frozenbit); @@ -98,6 +102,8 @@ transfer_all_new_dbs(DbInfoArr *old_db_arr, DbInfoArr *new_db_arr, *new_db = NULL; FileNameMap *mappings; int n_maps; + bool has_lotable = false; + bool has_loindex = false; /* * Advance past any databases that exist in the new cluster but not in @@ -117,22 +123,66 @@ transfer_all_new_dbs(DbInfoArr *old_db_arr, DbInfoArr *new_db_arr, mappings = gen_db_file_maps(old_db, new_db, &n_maps, old_pgdata, new_pgdata); - if (n_maps) - { - transfer_single_new_db(mappings, n_maps, old_tablespace); - } + transfer_single_new_db(mappings, n_maps, old_tablespace, + &has_lotable, &has_loindex); + + /* + * Remove the original pg_largeobject files created by initdb if they + * exist in the new cluster with different relfilenodes. This avoids + * leaving behind stray files unassociated with any relation. + */ + remove_stray_largeobject_files(new_db, has_lotable, has_loindex); + /* We allocate something even for n_maps == 0 */ pg_free(mappings); } } +/* + * If there's no relation in the cluster whose relfilenode is the OID of the + * largeobject table/index, then remove the stray file. It ought to have a + * single segment and fork. + */ +static void +remove_stray_largeobject_files(DbInfo *new_db, bool has_lotable, + bool has_loindex) +{ + char prefix[MAXPGPATH]; + char largeobj_file[MAXPGPATH]; + + if (new_db->db_tablespace[0] != '\0') + snprintf(prefix, sizeof(prefix), "%s/%s/%u", + new_db->db_tablespace, new_cluster.tablespace_suffix, + new_db->db_oid); + else + snprintf(prefix, sizeof(prefix), "%s/base/%u", + new_cluster.pgdata, new_db->db_oid); + + if (!has_lotable) + { + snprintf(largeobj_file, sizeof(largeobj_file), "%s/%u", + prefix, LargeObjectRelationId); + if (unlink(largeobj_file) != 0) + pg_fatal("Unable to remove %s.\n", largeobj_file); + } + + if (!has_loindex) + { + snprintf(largeobj_file, sizeof(largeobj_file), "%s/%u", + prefix, LargeObjectLOidPNIndexId); + if (unlink(largeobj_file) != 0) + pg_fatal("Unable to remove %s.\n", largeobj_file); + } +} + /* * transfer_single_new_db() * * create links for mappings stored in "maps" array. */ static void -transfer_single_new_db(FileNameMap *maps, int size, char *old_tablespace) +transfer_single_new_db(FileNameMap *maps, int size, char *old_tablespace, + bool *has_lotable, bool *has_loindex) { int mapnum; bool vm_must_add_frozenbit = false; @@ -146,6 +196,12 @@ transfer_single_new_db(FileNameMap *maps, int size, char *old_tablespace) for (mapnum = 0; mapnum < size; mapnum++) { + /* Keep track of whether a filenode matches the OID */ + if (maps[mapnum].relfilenumber == LargeObjectRelationId) + *has_lotable = true; + if (maps[mapnum].relfilenumber == LargeObjectLOidPNIndexId) + *has_loindex = true; + if (old_tablespace == NULL || strcmp(maps[mapnum].old_tablespace, old_tablespace) == 0) { diff --git a/src/bin/pg_upgrade/t/002_pg_upgrade.pl b/src/bin/pg_upgrade/t/002_pg_upgrade.pl index 2f9b13bf0ae..9ed48c4e06a 100644 --- a/src/bin/pg_upgrade/t/002_pg_upgrade.pl +++ b/src/bin/pg_upgrade/t/002_pg_upgrade.pl @@ -208,6 +208,8 @@ if (defined($ENV{oldinstall})) } } +$oldnode->safe_psql("regression", "VACUUM FULL pg_largeobject;"); + # In a VPATH build, we'll be started in the source directory, but we want # to run pg_upgrade in the build directory so that any files generated finish # in it, like delete_old_cluster.{sh,bat}. -- 2.17.1 --m+utxuhC6KVTvgNz-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v7 1/3] Add stats tests related to rewrite @ 2025-10-27 14:54 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Bertrand Drouvot @ 2025-10-27 14:54 UTC (permalink / raw) While there are existing rewrite tests, the stats behavior during rewrites doesn't have a good coverage. This patch adds some tests to record some stats after different rewrite scenarios. That is useful for a following patch where relation statistics will be keyed by relfilenode. We'll be able to test that the stats are still the ones we expect after rewrites. --- src/test/regress/expected/stats.out | 321 ++++ src/test/regress/expected/stats_1.out | 2255 +++++++++++++++++++++++++ src/test/regress/sql/stats.sql | 186 ++ 3 files changed, 2762 insertions(+) 91.8% src/test/regress/expected/ 8.1% src/test/regress/sql/ diff --git a/src/test/regress/expected/stats.out b/src/test/regress/expected/stats.out index 67e1860e984..06487e367d8 100644 --- a/src/test/regress/expected/stats.out +++ b/src/test/regress/expected/stats.out @@ -1910,4 +1910,325 @@ SELECT * FROM check_estimated_rows('SELECT * FROM table_fillfactor'); (1 row) DROP TABLE table_fillfactor; +-- Test some rewrites +CREATE TABLE test_2pc_timestamp (a int) WITH (autovacuum_enabled = false); +VACUUM ANALYZE test_2pc_timestamp; +SELECT last_analyze AS last_vacuum_analyze FROM pg_stat_all_tables WHERE relname = 'test_2pc_timestamp' \gset +BEGIN; +ALTER TABLE test_2pc_timestamp ALTER COLUMN a TYPE int; +PREPARE TRANSACTION 'test'; +COMMIT PREPARED 'test'; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT last_analyze = :'last_vacuum_analyze'::timestamptz FROM pg_stat_all_tables WHERE relname = 'test_2pc_timestamp'; + ?column? +---------- + t +(1 row) + +DROP TABLE test_2pc_timestamp; +CREATE TABLE test_2pc_rewrite_alone (a int); +INSERT INTO test_2pc_rewrite_alone VALUES (1); +BEGIN; +ALTER TABLE test_2pc_rewrite_alone ALTER COLUMN a TYPE bigint; +PREPARE TRANSACTION 'test'; +COMMIT PREPARED 'test'; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_2pc_rewrite_alone'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 1 | 1 | 0 +(1 row) + +DROP TABLE test_2pc_rewrite_alone; +CREATE TABLE test_2pc (a int); +INSERT INTO test_2pc VALUES (1); +BEGIN; +INSERT INTO test_2pc VALUES (1); +INSERT INTO test_2pc VALUES (2); +INSERT INTO test_2pc VALUES (3); +ALTER TABLE test_2pc ALTER COLUMN a TYPE bigint; +PREPARE TRANSACTION 'test'; +COMMIT PREPARED 'test'; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_2pc'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 4 | 4 | 0 +(1 row) + +DROP TABLE test_2pc; +CREATE TABLE test_2pc_multi (a int); +INSERT INTO test_2pc_multi VALUES (1); +BEGIN; +INSERT INTO test_2pc_multi VALUES (1); +INSERT INTO test_2pc_multi VALUES (2); +ALTER TABLE test_2pc_multi ALTER COLUMN a TYPE bigint; +INSERT INTO test_2pc_multi VALUES (3); +INSERT INTO test_2pc_multi VALUES (4); +ALTER TABLE test_2pc_multi ALTER COLUMN a TYPE int; +INSERT INTO test_2pc_multi VALUES (5); +PREPARE TRANSACTION 'test'; +COMMIT PREPARED 'test'; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_2pc_multi'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 6 | 6 | 0 +(1 row) + +DROP TABLE test_2pc_multi; +CREATE TABLE test_2pc_rewrite_alone_abort (a int); +INSERT INTO test_2pc_rewrite_alone_abort VALUES (1); +BEGIN; +ALTER TABLE test_2pc_rewrite_alone_abort ALTER COLUMN a TYPE bigint; +PREPARE TRANSACTION 'test'; +ROLLBACK PREPARED 'test'; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_2pc_rewrite_alone_abort'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 1 | 1 | 0 +(1 row) + +DROP TABLE test_2pc_rewrite_alone_abort; +CREATE TABLE test_2pc_abort (a int); +INSERT INTO test_2pc_abort VALUES (1); +BEGIN; +INSERT INTO test_2pc_abort VALUES (1); +INSERT INTO test_2pc_abort VALUES (2); +ALTER TABLE test_2pc_abort ALTER COLUMN a TYPE bigint; +INSERT INTO test_2pc_abort VALUES (3); +PREPARE TRANSACTION 'test'; +ROLLBACK PREPARED 'test'; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_2pc_abort'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 4 | 1 | 3 +(1 row) + +DROP TABLE test_2pc_abort; +CREATE TABLE test_2pc_savepoint (a int); +INSERT INTO test_2pc_savepoint VALUES (1); +BEGIN; +SAVEPOINT a; +INSERT INTO test_2pc_savepoint VALUES (1); +INSERT INTO test_2pc_savepoint VALUES (2); +ALTER TABLE test_2pc_savepoint ALTER COLUMN a TYPE bigint; +SAVEPOINT b; +INSERT INTO test_2pc_savepoint VALUES (3); +ALTER TABLE test_2pc_savepoint ALTER COLUMN a TYPE int; +SAVEPOINT c; +INSERT INTO test_2pc_savepoint VALUES (4); +INSERT INTO test_2pc_savepoint VALUES (5); +ROLLBACK TO SAVEPOINT b; +PREPARE TRANSACTION 'test'; +COMMIT PREPARED 'test'; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_2pc_savepoint'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 6 | 3 | 3 +(1 row) + +DROP TABLE test_2pc_savepoint; +-- Rewrite without 2PC +CREATE TABLE test_timestamp (a int) WITH (autovacuum_enabled = false); +VACUUM ANALYZE test_timestamp; +SELECT last_analyze AS last_vacuum_analyze FROM pg_stat_all_tables WHERE relname = 'test_timestamp' \gset +ALTER TABLE test_timestamp ALTER COLUMN a TYPE bigint; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT last_analyze = :'last_vacuum_analyze'::timestamptz FROM pg_stat_all_tables WHERE relname = 'test_timestamp'; + ?column? +---------- + t +(1 row) + +DROP TABLE test_timestamp; +CREATE TABLE test_alone (a int); +INSERT INTO test_alone VALUES (1); +BEGIN; +ALTER TABLE test_alone ALTER COLUMN a TYPE bigint; +COMMIT; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_alone'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 1 | 1 | 0 +(1 row) + +DROP TABLE test_alone; +CREATE TABLE test (a int); +INSERT INTO test VALUES (1); +BEGIN; +INSERT INTO test VALUES (1); +INSERT INTO test VALUES (2); +INSERT INTO test VALUES (3); +ALTER TABLE test ALTER COLUMN a TYPE bigint; +COMMIT; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 4 | 4 | 0 +(1 row) + +DROP TABLE test; +CREATE TABLE test_multi (a int); +INSERT INTO test_multi VALUES (1); +BEGIN; +INSERT INTO test_multi VALUES (1); +INSERT INTO test_multi VALUES (2); +ALTER TABLE test_multi ALTER COLUMN a TYPE bigint; +INSERT INTO test_multi VALUES (3); +INSERT INTO test_multi VALUES (4); +ALTER TABLE test_multi ALTER COLUMN a TYPE int; +INSERT INTO test_multi VALUES (5); +COMMIT; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_multi'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 6 | 6 | 0 +(1 row) + +DROP TABLE test_multi; +CREATE TABLE test_rewrite_alone_abort (a int); +INSERT INTO test_rewrite_alone_abort VALUES (1); +BEGIN; +ALTER TABLE test_rewrite_alone_abort ALTER COLUMN a TYPE bigint; +ROLLBACK; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_rewrite_alone_abort'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 1 | 1 | 0 +(1 row) + +DROP TABLE test_rewrite_alone_abort; +CREATE TABLE test_abort (a int); +INSERT INTO test_abort VALUES (1); +BEGIN; +INSERT INTO test_abort VALUES (1); +INSERT INTO test_abort VALUES (2); +ALTER TABLE test_abort ALTER COLUMN a TYPE bigint; +INSERT INTO test_abort VALUES (3); +ROLLBACK; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_abort'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 4 | 1 | 3 +(1 row) + +DROP TABLE test_abort; +CREATE TABLE test_savepoint (a int); +INSERT INTO test_savepoint VALUES (1); +BEGIN; +SAVEPOINT a; +INSERT INTO test_savepoint VALUES (1); +INSERT INTO test_savepoint VALUES (2); +ALTER TABLE test_savepoint ALTER COLUMN a TYPE bigint; +SAVEPOINT b; +INSERT INTO test_savepoint VALUES (3); +ALTER TABLE test_savepoint ALTER COLUMN a TYPE int; +SAVEPOINT c; +INSERT INTO test_savepoint VALUES (4); +INSERT INTO test_savepoint VALUES (5); +ROLLBACK TO SAVEPOINT b; +COMMIT; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_savepoint'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 6 | 3 | 3 +(1 row) + +DROP TABLE test_savepoint; +CREATE TABLE test_tbs (a int); +INSERT INTO test_tbs VALUES (1); +ALTER TABLE test_tbs SET TABLESPACE pg_default; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_tbs'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 1 | 1 | 0 +(1 row) + +DROP TABLE test_tbs; -- End of Stats Test diff --git a/src/test/regress/expected/stats_1.out b/src/test/regress/expected/stats_1.out new file mode 100644 index 00000000000..629e71fce0d --- /dev/null +++ b/src/test/regress/expected/stats_1.out @@ -0,0 +1,2255 @@ +-- +-- Test cumulative stats system +-- +-- Must be run after tenk2 has been created (by create_table), +-- populated (by create_misc) and indexed (by create_index). +-- +-- conditio sine qua non +SHOW track_counts; -- must be on + track_counts +-------------- + on +(1 row) + +-- List of backend types, contexts and objects tracked in pg_stat_io. +\a +SELECT backend_type, object, context FROM pg_stat_io + ORDER BY backend_type COLLATE "C", object COLLATE "C", context COLLATE "C"; +backend_type|object|context +autovacuum launcher|relation|bulkread +autovacuum launcher|relation|init +autovacuum launcher|relation|normal +autovacuum launcher|wal|init +autovacuum launcher|wal|normal +autovacuum worker|relation|bulkread +autovacuum worker|relation|init +autovacuum worker|relation|normal +autovacuum worker|relation|vacuum +autovacuum worker|wal|init +autovacuum worker|wal|normal +background worker|relation|bulkread +background worker|relation|bulkwrite +background worker|relation|init +background worker|relation|normal +background worker|relation|vacuum +background worker|temp relation|normal +background worker|wal|init +background worker|wal|normal +background writer|relation|init +background writer|relation|normal +background writer|wal|init +background writer|wal|normal +checkpointer|relation|init +checkpointer|relation|normal +checkpointer|wal|init +checkpointer|wal|normal +client backend|relation|bulkread +client backend|relation|bulkwrite +client backend|relation|init +client backend|relation|normal +client backend|relation|vacuum +client backend|temp relation|normal +client backend|wal|init +client backend|wal|normal +io worker|relation|bulkread +io worker|relation|bulkwrite +io worker|relation|init +io worker|relation|normal +io worker|relation|vacuum +io worker|temp relation|normal +io worker|wal|init +io worker|wal|normal +slotsync worker|relation|bulkread +slotsync worker|relation|bulkwrite +slotsync worker|relation|init +slotsync worker|relation|normal +slotsync worker|relation|vacuum +slotsync worker|temp relation|normal +slotsync worker|wal|init +slotsync worker|wal|normal +standalone backend|relation|bulkread +standalone backend|relation|bulkwrite +standalone backend|relation|init +standalone backend|relation|normal +standalone backend|relation|vacuum +standalone backend|wal|init +standalone backend|wal|normal +startup|relation|bulkread +startup|relation|bulkwrite +startup|relation|init +startup|relation|normal +startup|relation|vacuum +startup|wal|init +startup|wal|normal +walreceiver|wal|init +walreceiver|wal|normal +walsender|relation|bulkread +walsender|relation|bulkwrite +walsender|relation|init +walsender|relation|normal +walsender|relation|vacuum +walsender|temp relation|normal +walsender|wal|init +walsender|wal|normal +walsummarizer|wal|init +walsummarizer|wal|normal +walwriter|wal|init +walwriter|wal|normal +(79 rows) +\a +-- ensure that both seqscan and indexscan plans are allowed +SET enable_seqscan TO on; +SET enable_indexscan TO on; +-- for the moment, we don't want index-only scans here +SET enable_indexonlyscan TO off; +-- not enabled by default, but we want to test it... +SET track_functions TO 'all'; +-- record dboid for later use +SELECT oid AS dboid from pg_database where datname = current_database() \gset +-- save counters +BEGIN; +SET LOCAL stats_fetch_consistency = snapshot; +CREATE TABLE prevstats AS +SELECT t.seq_scan, t.seq_tup_read, t.idx_scan, t.idx_tup_fetch, + (b.heap_blks_read + b.heap_blks_hit) AS heap_blks, + (b.idx_blks_read + b.idx_blks_hit) AS idx_blks, + pg_stat_get_snapshot_timestamp() as snap_ts + FROM pg_catalog.pg_stat_user_tables AS t, + pg_catalog.pg_statio_user_tables AS b + WHERE t.relname='tenk2' AND b.relname='tenk2'; +COMMIT; +-- test effects of TRUNCATE on n_live_tup/n_dead_tup counters +CREATE TABLE trunc_stats_test(id serial); +CREATE TABLE trunc_stats_test1(id serial, stuff text); +CREATE TABLE trunc_stats_test2(id serial); +CREATE TABLE trunc_stats_test3(id serial, stuff text); +CREATE TABLE trunc_stats_test4(id serial); +-- check that n_live_tup is reset to 0 after truncate +INSERT INTO trunc_stats_test DEFAULT VALUES; +INSERT INTO trunc_stats_test DEFAULT VALUES; +INSERT INTO trunc_stats_test DEFAULT VALUES; +TRUNCATE trunc_stats_test; +-- test involving a truncate in a transaction; 4 ins but only 1 live +INSERT INTO trunc_stats_test1 DEFAULT VALUES; +INSERT INTO trunc_stats_test1 DEFAULT VALUES; +INSERT INTO trunc_stats_test1 DEFAULT VALUES; +UPDATE trunc_stats_test1 SET id = id + 10 WHERE id IN (1, 2); +DELETE FROM trunc_stats_test1 WHERE id = 3; +BEGIN; +UPDATE trunc_stats_test1 SET id = id + 100; +TRUNCATE trunc_stats_test1; +INSERT INTO trunc_stats_test1 DEFAULT VALUES; +COMMIT; +-- use a savepoint: 1 insert, 1 live +BEGIN; +INSERT INTO trunc_stats_test2 DEFAULT VALUES; +INSERT INTO trunc_stats_test2 DEFAULT VALUES; +SAVEPOINT p1; +INSERT INTO trunc_stats_test2 DEFAULT VALUES; +TRUNCATE trunc_stats_test2; +INSERT INTO trunc_stats_test2 DEFAULT VALUES; +RELEASE SAVEPOINT p1; +COMMIT; +-- rollback a savepoint: this should count 4 inserts and have 2 +-- live tuples after commit (and 2 dead ones due to aborted subxact) +BEGIN; +INSERT INTO trunc_stats_test3 DEFAULT VALUES; +INSERT INTO trunc_stats_test3 DEFAULT VALUES; +SAVEPOINT p1; +INSERT INTO trunc_stats_test3 DEFAULT VALUES; +INSERT INTO trunc_stats_test3 DEFAULT VALUES; +TRUNCATE trunc_stats_test3; +INSERT INTO trunc_stats_test3 DEFAULT VALUES; +ROLLBACK TO SAVEPOINT p1; +COMMIT; +-- rollback a truncate: this should count 2 inserts and produce 2 dead tuples +BEGIN; +INSERT INTO trunc_stats_test4 DEFAULT VALUES; +INSERT INTO trunc_stats_test4 DEFAULT VALUES; +TRUNCATE trunc_stats_test4; +INSERT INTO trunc_stats_test4 DEFAULT VALUES; +ROLLBACK; +-- do a seqscan +SELECT count(*) FROM tenk2; + count +------- + 10000 +(1 row) + +-- do an indexscan +-- make sure it is not a bitmap scan, which might skip fetching heap tuples +SET enable_bitmapscan TO off; +SELECT count(*) FROM tenk2 WHERE unique1 = 1; + count +------- + 1 +(1 row) + +RESET enable_bitmapscan; +-- ensure pending stats are flushed +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +-- check effects +BEGIN; +SET LOCAL stats_fetch_consistency = snapshot; +SELECT relname, n_tup_ins, n_tup_upd, n_tup_del, n_live_tup, n_dead_tup + FROM pg_stat_user_tables + WHERE relname like 'trunc_stats_test%' order by relname; + relname | n_tup_ins | n_tup_upd | n_tup_del | n_live_tup | n_dead_tup +-------------------+-----------+-----------+-----------+------------+------------ + trunc_stats_test | 3 | 0 | 0 | 0 | 0 + trunc_stats_test1 | 4 | 2 | 1 | 1 | 0 + trunc_stats_test2 | 1 | 0 | 0 | 1 | 0 + trunc_stats_test3 | 4 | 0 | 0 | 2 | 2 + trunc_stats_test4 | 2 | 0 | 0 | 0 | 2 +(5 rows) + +SELECT st.seq_scan >= pr.seq_scan + 1, + st.seq_tup_read >= pr.seq_tup_read + cl.reltuples, + st.idx_scan >= pr.idx_scan + 1, + st.idx_tup_fetch >= pr.idx_tup_fetch + 1 + FROM pg_stat_user_tables AS st, pg_class AS cl, prevstats AS pr + WHERE st.relname='tenk2' AND cl.relname='tenk2'; + ?column? | ?column? | ?column? | ?column? +----------+----------+----------+---------- + t | t | t | t +(1 row) + +SELECT st.heap_blks_read + st.heap_blks_hit >= pr.heap_blks + cl.relpages, + st.idx_blks_read + st.idx_blks_hit >= pr.idx_blks + 1 + FROM pg_statio_user_tables AS st, pg_class AS cl, prevstats AS pr + WHERE st.relname='tenk2' AND cl.relname='tenk2'; + ?column? | ?column? +----------+---------- + t | t +(1 row) + +SELECT pr.snap_ts < pg_stat_get_snapshot_timestamp() as snapshot_newer +FROM prevstats AS pr; + snapshot_newer +---------------- + t +(1 row) + +COMMIT; +---- +-- Basic tests for track_functions +--- +CREATE FUNCTION stats_test_func1() RETURNS VOID LANGUAGE plpgsql AS $$BEGIN END;$$; +SELECT 'stats_test_func1()'::regprocedure::oid AS stats_test_func1_oid \gset +CREATE FUNCTION stats_test_func2() RETURNS VOID LANGUAGE plpgsql AS $$BEGIN END;$$; +SELECT 'stats_test_func2()'::regprocedure::oid AS stats_test_func2_oid \gset +-- test that stats are accumulated +BEGIN; +SET LOCAL stats_fetch_consistency = none; +SELECT pg_stat_get_function_calls(:stats_test_func1_oid); + pg_stat_get_function_calls +---------------------------- + +(1 row) + +SELECT pg_stat_get_xact_function_calls(:stats_test_func1_oid); + pg_stat_get_xact_function_calls +--------------------------------- + +(1 row) + +SELECT stats_test_func1(); + stats_test_func1 +------------------ + +(1 row) + +SELECT pg_stat_get_xact_function_calls(:stats_test_func1_oid); + pg_stat_get_xact_function_calls +--------------------------------- + 1 +(1 row) + +SELECT stats_test_func1(); + stats_test_func1 +------------------ + +(1 row) + +SELECT pg_stat_get_xact_function_calls(:stats_test_func1_oid); + pg_stat_get_xact_function_calls +--------------------------------- + 2 +(1 row) + +SELECT pg_stat_get_function_calls(:stats_test_func1_oid); + pg_stat_get_function_calls +---------------------------- + 0 +(1 row) + +COMMIT; +-- Verify that function stats are not transactional +-- rolled back savepoint in committing transaction +BEGIN; +SELECT stats_test_func2(); + stats_test_func2 +------------------ + +(1 row) + +SAVEPOINT foo; +SELECT stats_test_func2(); + stats_test_func2 +------------------ + +(1 row) + +ROLLBACK TO SAVEPOINT foo; +SELECT pg_stat_get_xact_function_calls(:stats_test_func2_oid); + pg_stat_get_xact_function_calls +--------------------------------- + 2 +(1 row) + +SELECT stats_test_func2(); + stats_test_func2 +------------------ + +(1 row) + +COMMIT; +-- rolled back transaction +BEGIN; +SELECT stats_test_func2(); + stats_test_func2 +------------------ + +(1 row) + +ROLLBACK; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +-- check collected stats +SELECT funcname, calls FROM pg_stat_user_functions WHERE funcid = :stats_test_func1_oid; + funcname | calls +------------------+------- + stats_test_func1 | 2 +(1 row) + +SELECT funcname, calls FROM pg_stat_user_functions WHERE funcid = :stats_test_func2_oid; + funcname | calls +------------------+------- + stats_test_func2 | 4 +(1 row) + +-- check that a rolled back drop function stats leaves stats alive +BEGIN; +SELECT funcname, calls FROM pg_stat_user_functions WHERE funcid = :stats_test_func1_oid; + funcname | calls +------------------+------- + stats_test_func1 | 2 +(1 row) + +DROP FUNCTION stats_test_func1(); +-- shouldn't be visible via view +SELECT funcname, calls FROM pg_stat_user_functions WHERE funcid = :stats_test_func1_oid; + funcname | calls +----------+------- +(0 rows) + +-- but still via oid access +SELECT pg_stat_get_function_calls(:stats_test_func1_oid); + pg_stat_get_function_calls +---------------------------- + 2 +(1 row) + +ROLLBACK; +SELECT funcname, calls FROM pg_stat_user_functions WHERE funcid = :stats_test_func1_oid; + funcname | calls +------------------+------- + stats_test_func1 | 2 +(1 row) + +SELECT pg_stat_get_function_calls(:stats_test_func1_oid); + pg_stat_get_function_calls +---------------------------- + 2 +(1 row) + +-- check that function dropped in main transaction leaves no stats behind +BEGIN; +DROP FUNCTION stats_test_func1(); +COMMIT; +SELECT funcname, calls FROM pg_stat_user_functions WHERE funcid = :stats_test_func1_oid; + funcname | calls +----------+------- +(0 rows) + +SELECT pg_stat_get_function_calls(:stats_test_func1_oid); + pg_stat_get_function_calls +---------------------------- + +(1 row) + +-- check that function dropped in a subtransaction leaves no stats behind +BEGIN; +SELECT stats_test_func2(); + stats_test_func2 +------------------ + +(1 row) + +SAVEPOINT a; +SELECT stats_test_func2(); + stats_test_func2 +------------------ + +(1 row) + +SAVEPOINT b; +DROP FUNCTION stats_test_func2(); +COMMIT; +SELECT funcname, calls FROM pg_stat_user_functions WHERE funcid = :stats_test_func2_oid; + funcname | calls +----------+------- +(0 rows) + +SELECT pg_stat_get_function_calls(:stats_test_func2_oid); + pg_stat_get_function_calls +---------------------------- + +(1 row) + +-- Check that stats for relations are dropped. For that we need to access stats +-- by oid after the DROP TABLE. Save oids. +CREATE TABLE drop_stats_test(); +INSERT INTO drop_stats_test DEFAULT VALUES; +SELECT 'drop_stats_test'::regclass::oid AS drop_stats_test_oid \gset +CREATE TABLE drop_stats_test_xact(); +INSERT INTO drop_stats_test_xact DEFAULT VALUES; +SELECT 'drop_stats_test_xact'::regclass::oid AS drop_stats_test_xact_oid \gset +CREATE TABLE drop_stats_test_subxact(); +INSERT INTO drop_stats_test_subxact DEFAULT VALUES; +SELECT 'drop_stats_test_subxact'::regclass::oid AS drop_stats_test_subxact_oid \gset +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT pg_stat_get_live_tuples(:drop_stats_test_oid); + pg_stat_get_live_tuples +------------------------- + 1 +(1 row) + +DROP TABLE drop_stats_test; +SELECT pg_stat_get_live_tuples(:drop_stats_test_oid); + pg_stat_get_live_tuples +------------------------- + 0 +(1 row) + +SELECT pg_stat_get_xact_tuples_inserted(:drop_stats_test_oid); + pg_stat_get_xact_tuples_inserted +---------------------------------- + 0 +(1 row) + +-- check that rollback protects against having stats dropped and that local +-- modifications don't pose a problem +SELECT pg_stat_get_live_tuples(:drop_stats_test_xact_oid); + pg_stat_get_live_tuples +------------------------- + 1 +(1 row) + +SELECT pg_stat_get_tuples_inserted(:drop_stats_test_xact_oid); + pg_stat_get_tuples_inserted +----------------------------- + 1 +(1 row) + +SELECT pg_stat_get_xact_tuples_inserted(:drop_stats_test_xact_oid); + pg_stat_get_xact_tuples_inserted +---------------------------------- + 0 +(1 row) + +BEGIN; +INSERT INTO drop_stats_test_xact DEFAULT VALUES; +SELECT pg_stat_get_xact_tuples_inserted(:drop_stats_test_xact_oid); + pg_stat_get_xact_tuples_inserted +---------------------------------- + 1 +(1 row) + +DROP TABLE drop_stats_test_xact; +SELECT pg_stat_get_xact_tuples_inserted(:drop_stats_test_xact_oid); + pg_stat_get_xact_tuples_inserted +---------------------------------- + 0 +(1 row) + +ROLLBACK; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT pg_stat_get_live_tuples(:drop_stats_test_xact_oid); + pg_stat_get_live_tuples +------------------------- + 1 +(1 row) + +SELECT pg_stat_get_tuples_inserted(:drop_stats_test_xact_oid); + pg_stat_get_tuples_inserted +----------------------------- + 2 +(1 row) + +-- transactional drop +SELECT pg_stat_get_live_tuples(:drop_stats_test_xact_oid); + pg_stat_get_live_tuples +------------------------- + 1 +(1 row) + +SELECT pg_stat_get_tuples_inserted(:drop_stats_test_xact_oid); + pg_stat_get_tuples_inserted +----------------------------- + 2 +(1 row) + +BEGIN; +INSERT INTO drop_stats_test_xact DEFAULT VALUES; +SELECT pg_stat_get_xact_tuples_inserted(:drop_stats_test_xact_oid); + pg_stat_get_xact_tuples_inserted +---------------------------------- + 1 +(1 row) + +DROP TABLE drop_stats_test_xact; +SELECT pg_stat_get_xact_tuples_inserted(:drop_stats_test_xact_oid); + pg_stat_get_xact_tuples_inserted +---------------------------------- + 0 +(1 row) + +COMMIT; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT pg_stat_get_live_tuples(:drop_stats_test_xact_oid); + pg_stat_get_live_tuples +------------------------- + 0 +(1 row) + +SELECT pg_stat_get_tuples_inserted(:drop_stats_test_xact_oid); + pg_stat_get_tuples_inserted +----------------------------- + 0 +(1 row) + +-- savepoint rollback (2 levels) +SELECT pg_stat_get_live_tuples(:drop_stats_test_subxact_oid); + pg_stat_get_live_tuples +------------------------- + 1 +(1 row) + +BEGIN; +INSERT INTO drop_stats_test_subxact DEFAULT VALUES; +SAVEPOINT sp1; +INSERT INTO drop_stats_test_subxact DEFAULT VALUES; +SELECT pg_stat_get_xact_tuples_inserted(:drop_stats_test_subxact_oid); + pg_stat_get_xact_tuples_inserted +---------------------------------- + 2 +(1 row) + +SAVEPOINT sp2; +DROP TABLE drop_stats_test_subxact; +ROLLBACK TO SAVEPOINT sp2; +SELECT pg_stat_get_xact_tuples_inserted(:drop_stats_test_subxact_oid); + pg_stat_get_xact_tuples_inserted +---------------------------------- + 2 +(1 row) + +COMMIT; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT pg_stat_get_live_tuples(:drop_stats_test_subxact_oid); + pg_stat_get_live_tuples +------------------------- + 3 +(1 row) + +-- savepoint rolback (1 level) +SELECT pg_stat_get_live_tuples(:drop_stats_test_subxact_oid); + pg_stat_get_live_tuples +------------------------- + 3 +(1 row) + +BEGIN; +SAVEPOINT sp1; +DROP TABLE drop_stats_test_subxact; +SAVEPOINT sp2; +ROLLBACK TO SAVEPOINT sp1; +COMMIT; +SELECT pg_stat_get_live_tuples(:drop_stats_test_subxact_oid); + pg_stat_get_live_tuples +------------------------- + 3 +(1 row) + +-- and now actually drop +SELECT pg_stat_get_live_tuples(:drop_stats_test_subxact_oid); + pg_stat_get_live_tuples +------------------------- + 3 +(1 row) + +BEGIN; +SAVEPOINT sp1; +DROP TABLE drop_stats_test_subxact; +SAVEPOINT sp2; +RELEASE SAVEPOINT sp1; +COMMIT; +SELECT pg_stat_get_live_tuples(:drop_stats_test_subxact_oid); + pg_stat_get_live_tuples +------------------------- + 0 +(1 row) + +DROP TABLE trunc_stats_test, trunc_stats_test1, trunc_stats_test2, trunc_stats_test3, trunc_stats_test4; +DROP TABLE prevstats; +----- +-- Test that last_seq_scan, last_idx_scan are correctly maintained +-- +-- Perform test using a temporary table. That way autovacuum etc won't +-- interfere. To be able to check that timestamps increase, we sleep for 100ms +-- between tests, assuming that there aren't systems with a coarser timestamp +-- granularity. +----- +BEGIN; +CREATE TEMPORARY TABLE test_last_scan(idx_col int primary key, noidx_col int); +INSERT INTO test_last_scan(idx_col, noidx_col) VALUES(1, 1); +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT last_seq_scan, last_idx_scan FROM pg_stat_all_tables WHERE relid = 'test_last_scan'::regclass; + last_seq_scan | last_idx_scan +---------------+--------------- + | +(1 row) + +COMMIT; +SELECT stats_reset IS NOT NULL AS has_stats_reset + FROM pg_stat_all_tables WHERE relid = 'test_last_scan'::regclass; + has_stats_reset +----------------- + f +(1 row) + +SELECT pg_stat_reset_single_table_counters('test_last_scan'::regclass); + pg_stat_reset_single_table_counters +------------------------------------- + +(1 row) + +SELECT seq_scan, idx_scan, stats_reset IS NOT NULL AS has_stats_reset + FROM pg_stat_all_tables WHERE relid = 'test_last_scan'::regclass; + seq_scan | idx_scan | has_stats_reset +----------+----------+----------------- + 0 | 0 | t +(1 row) + +-- ensure we start out with exactly one index and sequential scan +BEGIN; +SET LOCAL enable_seqscan TO on; +SET LOCAL enable_indexscan TO on; +SET LOCAL enable_bitmapscan TO off; +EXPLAIN (COSTS off) SELECT count(*) FROM test_last_scan WHERE noidx_col = 1; + QUERY PLAN +---------------------------------- + Aggregate + -> Seq Scan on test_last_scan + Filter: (noidx_col = 1) +(3 rows) + +SELECT count(*) FROM test_last_scan WHERE noidx_col = 1; + count +------- + 1 +(1 row) + +SET LOCAL enable_seqscan TO off; +EXPLAIN (COSTS off) SELECT count(*) FROM test_last_scan WHERE idx_col = 1; + QUERY PLAN +-------------------------------------------------------------- + Aggregate + -> Index Scan using test_last_scan_pkey on test_last_scan + Index Cond: (idx_col = 1) +(3 rows) + +SELECT count(*) FROM test_last_scan WHERE idx_col = 1; + count +------- + 1 +(1 row) + +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +COMMIT; +-- fetch timestamps from before the next test +SELECT last_seq_scan AS test_last_seq, last_idx_scan AS test_last_idx +FROM pg_stat_all_tables WHERE relid = 'test_last_scan'::regclass \gset +SELECT pg_sleep(0.1); -- assume a minimum timestamp granularity of 100ms + pg_sleep +---------- + +(1 row) + +-- cause one sequential scan +BEGIN; +SET LOCAL enable_seqscan TO on; +SET LOCAL enable_indexscan TO off; +SET LOCAL enable_bitmapscan TO off; +EXPLAIN (COSTS off) SELECT count(*) FROM test_last_scan WHERE noidx_col = 1; + QUERY PLAN +---------------------------------- + Aggregate + -> Seq Scan on test_last_scan + Filter: (noidx_col = 1) +(3 rows) + +SELECT count(*) FROM test_last_scan WHERE noidx_col = 1; + count +------- + 1 +(1 row) + +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +COMMIT; +-- check that just sequential scan stats were incremented +SELECT seq_scan, :'test_last_seq' < last_seq_scan AS seq_ok, idx_scan, :'test_last_idx' = last_idx_scan AS idx_ok +FROM pg_stat_all_tables WHERE relid = 'test_last_scan'::regclass; + seq_scan | seq_ok | idx_scan | idx_ok +----------+--------+----------+-------- + 2 | t | 1 | t +(1 row) + +-- fetch timestamps from before the next test +SELECT last_seq_scan AS test_last_seq, last_idx_scan AS test_last_idx +FROM pg_stat_all_tables WHERE relid = 'test_last_scan'::regclass \gset +SELECT pg_sleep(0.1); + pg_sleep +---------- + +(1 row) + +-- cause one index scan +BEGIN; +SET LOCAL enable_seqscan TO off; +SET LOCAL enable_indexscan TO on; +SET LOCAL enable_bitmapscan TO off; +EXPLAIN (COSTS off) SELECT count(*) FROM test_last_scan WHERE idx_col = 1; + QUERY PLAN +-------------------------------------------------------------- + Aggregate + -> Index Scan using test_last_scan_pkey on test_last_scan + Index Cond: (idx_col = 1) +(3 rows) + +SELECT count(*) FROM test_last_scan WHERE idx_col = 1; + count +------- + 1 +(1 row) + +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +COMMIT; +-- check that just index scan stats were incremented +SELECT seq_scan, :'test_last_seq' = last_seq_scan AS seq_ok, idx_scan, :'test_last_idx' < last_idx_scan AS idx_ok +FROM pg_stat_all_tables WHERE relid = 'test_last_scan'::regclass; + seq_scan | seq_ok | idx_scan | idx_ok +----------+--------+----------+-------- + 2 | t | 2 | t +(1 row) + +-- fetch timestamps from before the next test +SELECT last_seq_scan AS test_last_seq, last_idx_scan AS test_last_idx +FROM pg_stat_all_tables WHERE relid = 'test_last_scan'::regclass \gset +SELECT pg_sleep(0.1); + pg_sleep +---------- + +(1 row) + +-- cause one bitmap index scan +BEGIN; +SET LOCAL enable_seqscan TO off; +SET LOCAL enable_indexscan TO off; +SET LOCAL enable_bitmapscan TO on; +EXPLAIN (COSTS off) SELECT count(*) FROM test_last_scan WHERE idx_col = 1; + QUERY PLAN +------------------------------------------------------ + Aggregate + -> Bitmap Heap Scan on test_last_scan + Recheck Cond: (idx_col = 1) + -> Bitmap Index Scan on test_last_scan_pkey + Index Cond: (idx_col = 1) +(5 rows) + +SELECT count(*) FROM test_last_scan WHERE idx_col = 1; + count +------- + 1 +(1 row) + +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +COMMIT; +-- check that just index scan stats were incremented +SELECT seq_scan, :'test_last_seq' = last_seq_scan AS seq_ok, idx_scan, :'test_last_idx' < last_idx_scan AS idx_ok +FROM pg_stat_all_tables WHERE relid = 'test_last_scan'::regclass; + seq_scan | seq_ok | idx_scan | idx_ok +----------+--------+----------+-------- + 2 | t | 3 | t +(1 row) + +-- check the stats in pg_stat_all_indexes +SELECT idx_scan, :'test_last_idx' < last_idx_scan AS idx_ok, + stats_reset IS NOT NULL AS has_stats_reset + FROM pg_stat_all_indexes WHERE indexrelid = 'test_last_scan_pkey'::regclass; + idx_scan | idx_ok | has_stats_reset +----------+--------+----------------- + 3 | t | f +(1 row) + +-- check that the stats in pg_stat_all_indexes are reset +SELECT pg_stat_reset_single_table_counters('test_last_scan_pkey'::regclass); + pg_stat_reset_single_table_counters +------------------------------------- + +(1 row) + +SELECT idx_scan, stats_reset IS NOT NULL AS has_stats_reset + FROM pg_stat_all_indexes WHERE indexrelid = 'test_last_scan_pkey'::regclass; + idx_scan | has_stats_reset +----------+----------------- + 0 | t +(1 row) + +----- +-- Test reset of some stats for shared table +----- +-- This updates the comment of the database currently in use in +-- pg_shdescription with a fake value, then sets it back to its +-- original value. +SELECT shobj_description(d.oid, 'pg_database') as description_before + FROM pg_database d WHERE datname = current_database() \gset +-- force some stats in pg_shdescription. +BEGIN; +SELECT current_database() as datname \gset +COMMENT ON DATABASE :"datname" IS 'This is a test comment'; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +COMMIT; +-- check that the stats are reset. +SELECT (n_tup_ins + n_tup_upd) > 0 AS has_data FROM pg_stat_all_tables + WHERE relid = 'pg_shdescription'::regclass; + has_data +---------- + t +(1 row) + +SELECT pg_stat_reset_single_table_counters('pg_shdescription'::regclass); + pg_stat_reset_single_table_counters +------------------------------------- + +(1 row) + +SELECT (n_tup_ins + n_tup_upd) > 0 AS has_data FROM pg_stat_all_tables + WHERE relid = 'pg_shdescription'::regclass; + has_data +---------- + f +(1 row) + +-- set back comment +\if :{?description_before} + COMMENT ON DATABASE :"datname" IS :'description_before'; +\else + COMMENT ON DATABASE :"datname" IS NULL; +\endif +----- +-- Test that various stats views are being properly populated +----- +-- Test that sessions is incremented when a new session is started in pg_stat_database +SELECT sessions AS db_stat_sessions FROM pg_stat_database WHERE datname = (SELECT current_database()) \gset +\c +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT sessions > :db_stat_sessions FROM pg_stat_database WHERE datname = (SELECT current_database()); + ?column? +---------- + t +(1 row) + +-- Test pg_stat_checkpointer checkpointer-related stats, together with pg_stat_wal +SELECT num_requested AS rqst_ckpts_before FROM pg_stat_checkpointer \gset +-- Test pg_stat_wal +SELECT wal_bytes AS wal_bytes_before FROM pg_stat_wal \gset +-- Test pg_stat_get_backend_wal() +SELECT wal_bytes AS backend_wal_bytes_before from pg_stat_get_backend_wal(pg_backend_pid()) \gset +-- Make a temp table so our temp schema exists +CREATE TEMP TABLE test_stats_temp AS SELECT 17; +DROP TABLE test_stats_temp; +-- Checkpoint twice: The checkpointer reports stats after reporting completion +-- of the checkpoint. But after a second checkpoint we'll see at least the +-- results of the first. +-- +-- While at it, test checkpoint options. Note that we don't test MODE SPREAD +-- because it would prolong the test. +CHECKPOINT (WRONG); +ERROR: unrecognized CHECKPOINT option "wrong" +LINE 1: CHECKPOINT (WRONG); + ^ +CHECKPOINT (MODE WRONG); +ERROR: unrecognized MODE option "wrong" +LINE 1: CHECKPOINT (MODE WRONG); + ^ +CHECKPOINT (MODE FAST, FLUSH_UNLOGGED FALSE); +CHECKPOINT (FLUSH_UNLOGGED); +SELECT num_requested > :rqst_ckpts_before FROM pg_stat_checkpointer; + ?column? +---------- + t +(1 row) + +SELECT wal_bytes > :wal_bytes_before FROM pg_stat_wal; + ?column? +---------- + t +(1 row) + +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT wal_bytes > :backend_wal_bytes_before FROM pg_stat_get_backend_wal(pg_backend_pid()); + ?column? +---------- + t +(1 row) + +-- Test pg_stat_get_backend_idset() and some allied functions. +-- In particular, verify that their notion of backend ID matches +-- our temp schema index. +SELECT (current_schemas(true))[1] = ('pg_temp_' || beid::text) AS match +FROM pg_stat_get_backend_idset() beid +WHERE pg_stat_get_backend_pid(beid) = pg_backend_pid(); + match +------- + t +(1 row) + +----- +-- Test that resetting stats works for reset timestamp +----- +-- Test that reset_slru with a specified SLRU works. +SELECT stats_reset AS slru_commit_ts_reset_ts FROM pg_stat_slru WHERE name = 'commit_timestamp' \gset +SELECT stats_reset AS slru_notify_reset_ts FROM pg_stat_slru WHERE name = 'notify' \gset +SELECT pg_stat_reset_slru('commit_timestamp'); + pg_stat_reset_slru +-------------------- + +(1 row) + +SELECT stats_reset > :'slru_commit_ts_reset_ts'::timestamptz FROM pg_stat_slru WHERE name = 'commit_timestamp'; + ?column? +---------- + t +(1 row) + +SELECT stats_reset AS slru_commit_ts_reset_ts FROM pg_stat_slru WHERE name = 'commit_timestamp' \gset +-- Test that multiple SLRUs are reset when no specific SLRU provided to reset function +SELECT pg_stat_reset_slru(); + pg_stat_reset_slru +-------------------- + +(1 row) + +SELECT stats_reset > :'slru_commit_ts_reset_ts'::timestamptz FROM pg_stat_slru WHERE name = 'commit_timestamp'; + ?column? +---------- + t +(1 row) + +SELECT stats_reset > :'slru_notify_reset_ts'::timestamptz FROM pg_stat_slru WHERE name = 'notify'; + ?column? +---------- + t +(1 row) + +-- Test that reset_shared with archiver specified as the stats type works +SELECT stats_reset AS archiver_reset_ts FROM pg_stat_archiver \gset +SELECT pg_stat_reset_shared('archiver'); + pg_stat_reset_shared +---------------------- + +(1 row) + +SELECT stats_reset > :'archiver_reset_ts'::timestamptz FROM pg_stat_archiver; + ?column? +---------- + t +(1 row) + +-- Test that reset_shared with bgwriter specified as the stats type works +SELECT stats_reset AS bgwriter_reset_ts FROM pg_stat_bgwriter \gset +SELECT pg_stat_reset_shared('bgwriter'); + pg_stat_reset_shared +---------------------- + +(1 row) + +SELECT stats_reset > :'bgwriter_reset_ts'::timestamptz FROM pg_stat_bgwriter; + ?column? +---------- + t +(1 row) + +-- Test that reset_shared with checkpointer specified as the stats type works +SELECT stats_reset AS checkpointer_reset_ts FROM pg_stat_checkpointer \gset +SELECT pg_stat_reset_shared('checkpointer'); + pg_stat_reset_shared +---------------------- + +(1 row) + +SELECT stats_reset > :'checkpointer_reset_ts'::timestamptz FROM pg_stat_checkpointer; + ?column? +---------- + t +(1 row) + +-- Test that reset_shared with recovery_prefetch specified as the stats type works +SELECT stats_reset AS recovery_prefetch_reset_ts FROM pg_stat_recovery_prefetch \gset +SELECT pg_stat_reset_shared('recovery_prefetch'); + pg_stat_reset_shared +---------------------- + +(1 row) + +SELECT stats_reset > :'recovery_prefetch_reset_ts'::timestamptz FROM pg_stat_recovery_prefetch; + ?column? +---------- + t +(1 row) + +-- Test that reset_shared with slru specified as the stats type works +SELECT max(stats_reset) AS slru_reset_ts FROM pg_stat_slru \gset +SELECT pg_stat_reset_shared('slru'); + pg_stat_reset_shared +---------------------- + +(1 row) + +SELECT max(stats_reset) > :'slru_reset_ts'::timestamptz FROM pg_stat_slru; + ?column? +---------- + t +(1 row) + +-- Test that reset_shared with wal specified as the stats type works +SELECT stats_reset AS wal_reset_ts FROM pg_stat_wal \gset +SELECT pg_stat_reset_shared('wal'); + pg_stat_reset_shared +---------------------- + +(1 row) + +SELECT stats_reset > :'wal_reset_ts'::timestamptz FROM pg_stat_wal; + ?column? +---------- + t +(1 row) + +-- Test error case for reset_shared with unknown stats type +SELECT pg_stat_reset_shared('unknown'); +ERROR: unrecognized reset target: "unknown" +HINT: Target must be "archiver", "bgwriter", "checkpointer", "io", "recovery_prefetch", "slru", or "wal". +-- Test that reset works for pg_stat_database +-- Since pg_stat_database stats_reset starts out as NULL, reset it once first so we have something to compare it to +SELECT pg_stat_reset(); + pg_stat_reset +--------------- + +(1 row) + +SELECT stats_reset AS db_reset_ts FROM pg_stat_database WHERE datname = (SELECT current_database()) \gset +SELECT pg_stat_reset(); + pg_stat_reset +--------------- + +(1 row) + +SELECT stats_reset > :'db_reset_ts'::timestamptz FROM pg_stat_database WHERE datname = (SELECT current_database()); + ?column? +---------- + t +(1 row) + +---- +-- pg_stat_get_snapshot_timestamp behavior +---- +BEGIN; +SET LOCAL stats_fetch_consistency = snapshot; +-- no snapshot yet, return NULL +SELECT pg_stat_get_snapshot_timestamp(); + pg_stat_get_snapshot_timestamp +-------------------------------- + +(1 row) + +-- any attempt at accessing stats will build snapshot +SELECT pg_stat_get_function_calls(0); + pg_stat_get_function_calls +---------------------------- + +(1 row) + +SELECT pg_stat_get_snapshot_timestamp() >= NOW(); + ?column? +---------- + t +(1 row) + +-- shows NULL again after clearing +SELECT pg_stat_clear_snapshot(); + pg_stat_clear_snapshot +------------------------ + +(1 row) + +SELECT pg_stat_get_snapshot_timestamp(); + pg_stat_get_snapshot_timestamp +-------------------------------- + +(1 row) + +COMMIT; +---- +-- Changing stats_fetch_consistency in a transaction. +---- +BEGIN; +-- Stats filled under the cache mode +SET LOCAL stats_fetch_consistency = cache; +SELECT pg_stat_get_function_calls(0); + pg_stat_get_function_calls +---------------------------- + +(1 row) + +SELECT pg_stat_get_snapshot_timestamp() IS NOT NULL AS snapshot_ok; + snapshot_ok +------------- + f +(1 row) + +-- Success in accessing pre-existing snapshot data. +SET LOCAL stats_fetch_consistency = snapshot; +SELECT pg_stat_get_snapshot_timestamp() IS NOT NULL AS snapshot_ok; + snapshot_ok +------------- + f +(1 row) + +SELECT pg_stat_get_function_calls(0); + pg_stat_get_function_calls +---------------------------- + +(1 row) + +SELECT pg_stat_get_snapshot_timestamp() IS NOT NULL AS snapshot_ok; + snapshot_ok +------------- + t +(1 row) + +-- Snapshot cleared. +SET LOCAL stats_fetch_consistency = none; +SELECT pg_stat_get_snapshot_timestamp() IS NOT NULL AS snapshot_ok; + snapshot_ok +------------- + f +(1 row) + +SELECT pg_stat_get_function_calls(0); + pg_stat_get_function_calls +---------------------------- + +(1 row) + +SELECT pg_stat_get_snapshot_timestamp() IS NOT NULL AS snapshot_ok; + snapshot_ok +------------- + f +(1 row) + +ROLLBACK; +---- +-- pg_stat_have_stats behavior +---- +-- fixed-numbered stats exist +SELECT pg_stat_have_stats('bgwriter', 0, 0); + pg_stat_have_stats +-------------------- + t +(1 row) + +-- unknown stats kinds error out +SELECT pg_stat_have_stats('zaphod', 0, 0); +ERROR: invalid statistics kind: "zaphod" +-- db stats have objid 0 +SELECT pg_stat_have_stats('database', :dboid, 1); + pg_stat_have_stats +-------------------- + f +(1 row) + +SELECT pg_stat_have_stats('database', :dboid, 0); + pg_stat_have_stats +-------------------- + t +(1 row) + +-- pg_stat_have_stats returns true for committed index creation +CREATE table stats_test_tab1 as select generate_series(1,10) a; +CREATE index stats_test_idx1 on stats_test_tab1(a); +SELECT 'stats_test_idx1'::regclass::oid AS stats_test_idx1_oid \gset +SET enable_seqscan TO off; +select a from stats_test_tab1 where a = 3; + a +--- + 3 +(1 row) + +SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid); + pg_stat_have_stats +-------------------- + t +(1 row) + +-- pg_stat_have_stats returns false for dropped index with stats +SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid); + pg_stat_have_stats +-------------------- + t +(1 row) + +DROP index stats_test_idx1; +SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid); + pg_stat_have_stats +-------------------- + f +(1 row) + +-- pg_stat_have_stats returns false for rolled back index creation +BEGIN; +CREATE index stats_test_idx1 on stats_test_tab1(a); +SELECT 'stats_test_idx1'::regclass::oid AS stats_test_idx1_oid \gset +select a from stats_test_tab1 where a = 3; + a +--- + 3 +(1 row) + +SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid); + pg_stat_have_stats +-------------------- + t +(1 row) + +ROLLBACK; +SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid); + pg_stat_have_stats +-------------------- + f +(1 row) + +-- pg_stat_have_stats returns true for reindex CONCURRENTLY +CREATE index stats_test_idx1 on stats_test_tab1(a); +SELECT 'stats_test_idx1'::regclass::oid AS stats_test_idx1_oid \gset +select a from stats_test_tab1 where a = 3; + a +--- + 3 +(1 row) + +SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid); + pg_stat_have_stats +-------------------- + t +(1 row) + +REINDEX index CONCURRENTLY stats_test_idx1; +-- false for previous oid +SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid); + pg_stat_have_stats +-------------------- + f +(1 row) + +-- true for new oid +SELECT 'stats_test_idx1'::regclass::oid AS stats_test_idx1_oid \gset +SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid); + pg_stat_have_stats +-------------------- + t +(1 row) + +-- pg_stat_have_stats returns true for a rolled back drop index with stats +BEGIN; +SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid); + pg_stat_have_stats +-------------------- + t +(1 row) + +DROP index stats_test_idx1; +ROLLBACK; +SELECT pg_stat_have_stats('relation', :dboid, :stats_test_idx1_oid); + pg_stat_have_stats +-------------------- + t +(1 row) + +-- put enable_seqscan back to on +SET enable_seqscan TO on; +-- ensure that stats accessors handle NULL input correctly +SELECT pg_stat_get_replication_slot(NULL); + pg_stat_get_replication_slot +------------------------------ + +(1 row) + +SELECT pg_stat_get_subscription_stats(NULL); + pg_stat_get_subscription_stats +-------------------------------- + +(1 row) + +-- Test that the following operations are tracked in pg_stat_io and in +-- backend stats: +-- - reads of target blocks into shared buffers +-- - writes of shared buffers to permanent storage +-- - extends of relations using shared buffers +-- - fsyncs done to ensure the durability of data dirtying shared buffers +-- - shared buffer hits +-- - WAL writes and fsyncs in IOContext IOCONTEXT_NORMAL +-- There is no test for blocks evicted from shared buffers, because we cannot +-- be sure of the state of shared buffers at the point the test is run. +-- Create a regular table and insert some data to generate IOCONTEXT_NORMAL +-- extends. +SELECT pid AS checkpointer_pid FROM pg_stat_activity + WHERE backend_type = 'checkpointer' \gset +SELECT sum(extends) AS io_sum_shared_before_extends + FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset +SELECT sum(extends) AS my_io_sum_shared_before_extends + FROM pg_stat_get_backend_io(pg_backend_pid()) + WHERE context = 'normal' AND object = 'relation' \gset +SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs + FROM pg_stat_io + WHERE object = 'relation' \gset io_sum_shared_before_ +SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs + FROM pg_stat_get_backend_io(pg_backend_pid()) + WHERE object = 'relation' \gset my_io_sum_shared_before_ +SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs + FROM pg_stat_io + WHERE context = 'normal' AND object = 'wal' \gset io_sum_wal_normal_before_ +CREATE TABLE test_io_shared(a int); +INSERT INTO test_io_shared SELECT i FROM generate_series(1,100)i; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT sum(extends) AS io_sum_shared_after_extends + FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset +SELECT :io_sum_shared_after_extends > :io_sum_shared_before_extends; + ?column? +---------- + t +(1 row) + +SELECT sum(extends) AS my_io_sum_shared_after_extends + FROM pg_stat_get_backend_io(pg_backend_pid()) + WHERE context = 'normal' AND object = 'relation' \gset +SELECT :my_io_sum_shared_after_extends > :my_io_sum_shared_before_extends; + ?column? +---------- + t +(1 row) + +-- After a checkpoint, there should be some additional IOCONTEXT_NORMAL writes +-- and fsyncs in the global stats (usually not for the backend). +-- See comment above for rationale for two explicit CHECKPOINTs. +CHECKPOINT; +CHECKPOINT; +SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs + FROM pg_stat_io + WHERE object = 'relation' \gset io_sum_shared_after_ +SELECT :io_sum_shared_after_writes > :io_sum_shared_before_writes; + ?column? +---------- + t +(1 row) + +SELECT current_setting('fsync') = 'off' + OR :io_sum_shared_after_fsyncs > :io_sum_shared_before_fsyncs; + ?column? +---------- + t +(1 row) + +SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs + FROM pg_stat_get_backend_io(pg_backend_pid()) + WHERE object = 'relation' \gset my_io_sum_shared_after_ +SELECT :my_io_sum_shared_after_writes >= :my_io_sum_shared_before_writes; + ?column? +---------- + t +(1 row) + +SELECT current_setting('fsync') = 'off' + OR :my_io_sum_shared_after_fsyncs >= :my_io_sum_shared_before_fsyncs; + ?column? +---------- + t +(1 row) + +SELECT sum(writes) AS writes, sum(fsyncs) AS fsyncs + FROM pg_stat_io + WHERE context = 'normal' AND object = 'wal' \gset io_sum_wal_normal_after_ +SELECT current_setting('synchronous_commit') = 'on'; + ?column? +---------- + t +(1 row) + +SELECT :io_sum_wal_normal_after_writes > :io_sum_wal_normal_before_writes; + ?column? +---------- + t +(1 row) + +SELECT current_setting('fsync') = 'off' + OR current_setting('wal_sync_method') IN ('open_sync', 'open_datasync') + OR :io_sum_wal_normal_after_fsyncs > :io_sum_wal_normal_before_fsyncs; + ?column? +---------- + t +(1 row) + +-- Change the tablespace so that the table is rewritten directly, then SELECT +-- from it to cause it to be read back into shared buffers. +SELECT sum(reads) AS io_sum_shared_before_reads + FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset +-- Do this in a transaction to prevent spurious failures due to concurrent accesses to our newly +-- rewritten table, e.g. by autovacuum. +BEGIN; +ALTER TABLE test_io_shared SET TABLESPACE regress_tblspace; +-- SELECT from the table so that the data is read into shared buffers and +-- context 'normal', object 'relation' reads are counted. +SELECT COUNT(*) FROM test_io_shared; + count +------- + 100 +(1 row) + +COMMIT; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT sum(reads) AS io_sum_shared_after_reads + FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset +SELECT :io_sum_shared_after_reads > :io_sum_shared_before_reads; + ?column? +---------- + t +(1 row) + +SELECT sum(hits) AS io_sum_shared_before_hits + FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset +-- Select from the table again to count hits. +-- Ensure we generate hits by forcing a nested loop self-join with no +-- materialize node. The outer side's buffer will stay pinned, preventing its +-- eviction, while we loop through the inner side and generate hits. +BEGIN; +SET LOCAL enable_nestloop TO on; SET LOCAL enable_mergejoin TO off; +SET LOCAL enable_hashjoin TO off; SET LOCAL enable_material TO off; +-- ensure plan stays as we expect it to +EXPLAIN (COSTS OFF) SELECT COUNT(*) FROM test_io_shared t1 INNER JOIN test_io_shared t2 USING (a); + QUERY PLAN +------------------------------------------- + Aggregate + -> Nested Loop + Join Filter: (t1.a = t2.a) + -> Seq Scan on test_io_shared t1 + -> Seq Scan on test_io_shared t2 +(5 rows) + +SELECT COUNT(*) FROM test_io_shared t1 INNER JOIN test_io_shared t2 USING (a); + count +------- + 100 +(1 row) + +COMMIT; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT sum(hits) AS io_sum_shared_after_hits + FROM pg_stat_io WHERE context = 'normal' AND object = 'relation' \gset +SELECT :io_sum_shared_after_hits > :io_sum_shared_before_hits; + ?column? +---------- + t +(1 row) + +DROP TABLE test_io_shared; +-- Test that the follow IOCONTEXT_LOCAL IOOps are tracked in pg_stat_io: +-- - eviction of local buffers in order to reuse them +-- - reads of temporary table blocks into local buffers +-- - writes of local buffers to permanent storage +-- - extends of temporary tables +-- Set temp_buffers to its minimum so that we can trigger writes with fewer +-- inserted tuples. Do so in a new session in case temporary tables have been +-- accessed by previous tests in this session. +\c +SET temp_buffers TO 100; +CREATE TEMPORARY TABLE test_io_local(a int, b TEXT); +SELECT sum(extends) AS extends, sum(evictions) AS evictions, sum(writes) AS writes + FROM pg_stat_io + WHERE context = 'normal' AND object = 'temp relation' \gset io_sum_local_before_ +-- Insert tuples into the temporary table, generating extends in the stats. +-- Insert enough values that we need to reuse and write out dirty local +-- buffers, generating evictions and writes. +INSERT INTO test_io_local SELECT generate_series(1, 5000) as id, repeat('a', 200); +-- Ensure the table is large enough to exceed our temp_buffers setting. +SELECT pg_relation_size('test_io_local') / current_setting('block_size')::int8 > 100; + ?column? +---------- + t +(1 row) + +SELECT sum(reads) AS io_sum_local_before_reads + FROM pg_stat_io WHERE context = 'normal' AND object = 'temp relation' \gset +-- Read in evicted buffers, generating reads. +SELECT COUNT(*) FROM test_io_local; + count +------- + 5000 +(1 row) + +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT sum(evictions) AS evictions, + sum(reads) AS reads, + sum(writes) AS writes, + sum(extends) AS extends + FROM pg_stat_io + WHERE context = 'normal' AND object = 'temp relation' \gset io_sum_local_after_ +SELECT :io_sum_local_after_evictions > :io_sum_local_before_evictions, + :io_sum_local_after_reads > :io_sum_local_before_reads, + :io_sum_local_after_writes > :io_sum_local_before_writes, + :io_sum_local_after_extends > :io_sum_local_before_extends; + ?column? | ?column? | ?column? | ?column? +----------+----------+----------+---------- + t | t | t | t +(1 row) + +-- Change the tablespaces so that the temporary table is rewritten to other +-- local buffers, exercising a different codepath than standard local buffer +-- writes. +ALTER TABLE test_io_local SET TABLESPACE regress_tblspace; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT sum(writes) AS io_sum_local_new_tblspc_writes + FROM pg_stat_io WHERE context = 'normal' AND object = 'temp relation' \gset +SELECT :io_sum_local_new_tblspc_writes > :io_sum_local_after_writes; + ?column? +---------- + t +(1 row) + +RESET temp_buffers; +-- Test that reuse of strategy buffers and reads of blocks into these reused +-- buffers while VACUUMing are tracked in pg_stat_io. If there is sufficient +-- demand for shared buffers from concurrent queries, some buffers may be +-- pinned by other backends before they can be reused. In such cases, the +-- backend will evict a buffer from outside the ring and add it to the +-- ring. This is considered an eviction and not a reuse. +-- Set wal_skip_threshold smaller than the expected size of +-- test_io_vac_strategy so that, even if wal_level is minimal, VACUUM FULL will +-- fsync the newly rewritten test_io_vac_strategy instead of writing it to WAL. +-- Writing it to WAL will result in the newly written relation pages being in +-- shared buffers -- preventing us from testing BAS_VACUUM BufferAccessStrategy +-- reads. +SET wal_skip_threshold = '1 kB'; +SELECT sum(reuses) AS reuses, sum(reads) AS reads, sum(evictions) AS evictions + FROM pg_stat_io WHERE context = 'vacuum' \gset io_sum_vac_strategy_before_ +CREATE TABLE test_io_vac_strategy(a int, b int) WITH (autovacuum_enabled = 'false'); +INSERT INTO test_io_vac_strategy SELECT i, i from generate_series(1, 4500)i; +-- Ensure that the next VACUUM will need to perform IO by rewriting the table +-- first with VACUUM (FULL). +VACUUM (FULL) test_io_vac_strategy; +-- Use the minimum BUFFER_USAGE_LIMIT to cause reuses or evictions with the +-- smallest table possible. +VACUUM (PARALLEL 0, BUFFER_USAGE_LIMIT 128) test_io_vac_strategy; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT sum(reuses) AS reuses, sum(reads) AS reads, sum(evictions) AS evictions + FROM pg_stat_io WHERE context = 'vacuum' \gset io_sum_vac_strategy_after_ +SELECT :io_sum_vac_strategy_after_reads > :io_sum_vac_strategy_before_reads; + ?column? +---------- + t +(1 row) + +SELECT (:io_sum_vac_strategy_after_reuses + :io_sum_vac_strategy_after_evictions) > + (:io_sum_vac_strategy_before_reuses + :io_sum_vac_strategy_before_evictions); + ?column? +---------- + t +(1 row) + +RESET wal_skip_threshold; +-- Test that extends done by a CTAS, which uses a BAS_BULKWRITE +-- BufferAccessStrategy, are tracked in pg_stat_io. +SELECT sum(extends) AS io_sum_bulkwrite_strategy_extends_before + FROM pg_stat_io WHERE context = 'bulkwrite' \gset +CREATE TABLE test_io_bulkwrite_strategy AS SELECT i FROM generate_series(1,100)i; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT sum(extends) AS io_sum_bulkwrite_strategy_extends_after + FROM pg_stat_io WHERE context = 'bulkwrite' \gset +SELECT :io_sum_bulkwrite_strategy_extends_after > :io_sum_bulkwrite_strategy_extends_before; + ?column? +---------- + t +(1 row) + +-- Test IO stats reset +SELECT pg_stat_have_stats('io', 0, 0); + pg_stat_have_stats +-------------------- + t +(1 row) + +SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_pre_reset + FROM pg_stat_io \gset +SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_pre_reset + FROM pg_stat_get_backend_io(pg_backend_pid()) \gset +SELECT pg_stat_reset_shared('io'); + pg_stat_reset_shared +---------------------- + +(1 row) + +SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS io_stats_post_reset + FROM pg_stat_io \gset +SELECT :io_stats_post_reset < :io_stats_pre_reset; + ?column? +---------- + t +(1 row) + +SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_reset + FROM pg_stat_get_backend_io(pg_backend_pid()) \gset +-- pg_stat_reset_shared() did not reset backend IO stats +SELECT :my_io_stats_pre_reset <= :my_io_stats_post_reset; + ?column? +---------- + t +(1 row) + +-- but pg_stat_reset_backend_stats() does +SELECT pg_stat_reset_backend_stats(pg_backend_pid()); + pg_stat_reset_backend_stats +----------------------------- + +(1 row) + +SELECT sum(evictions) + sum(reuses) + sum(extends) + sum(fsyncs) + sum(reads) + sum(writes) + sum(writebacks) + sum(hits) AS my_io_stats_post_backend_reset + FROM pg_stat_get_backend_io(pg_backend_pid()) \gset +SELECT :my_io_stats_pre_reset > :my_io_stats_post_backend_reset; + ?column? +---------- + t +(1 row) + +-- Check invalid input for pg_stat_get_backend_io() +SELECT pg_stat_get_backend_io(NULL); + pg_stat_get_backend_io +------------------------ +(0 rows) + +SELECT pg_stat_get_backend_io(0); + pg_stat_get_backend_io +------------------------ +(0 rows) + +-- Auxiliary processes return no data. +SELECT pg_stat_get_backend_io(:checkpointer_pid); + pg_stat_get_backend_io +------------------------ +(0 rows) + +-- test BRIN index doesn't block HOT update +CREATE TABLE brin_hot ( + id integer PRIMARY KEY, + val integer NOT NULL +) WITH (autovacuum_enabled = off, fillfactor = 70); +INSERT INTO brin_hot SELECT *, 0 FROM generate_series(1, 235); +CREATE INDEX val_brin ON brin_hot using brin(val); +CREATE FUNCTION wait_for_hot_stats() RETURNS void AS $$ +DECLARE + start_time timestamptz := clock_timestamp(); + updated bool; +BEGIN + -- we don't want to wait forever; loop will exit after 30 seconds + FOR i IN 1 .. 300 LOOP + SELECT (pg_stat_get_tuples_hot_updated('brin_hot'::regclass::oid) > 0) INTO updated; + EXIT WHEN updated; + + -- wait a little + PERFORM pg_sleep_for('100 milliseconds'); + -- reset stats snapshot so we can test again + PERFORM pg_stat_clear_snapshot(); + END LOOP; + -- report time waited in postmaster log (where it won't change test output) + RAISE log 'wait_for_hot_stats delayed % seconds', + EXTRACT(epoch FROM clock_timestamp() - start_time); +END +$$ LANGUAGE plpgsql; +UPDATE brin_hot SET val = -3 WHERE id = 42; +-- We can't just call wait_for_hot_stats() at this point, because we only +-- transmit stats when the session goes idle, and we probably didn't +-- transmit the last couple of counts yet thanks to the rate-limiting logic +-- in pgstat_report_stat(). But instead of waiting for the rate limiter's +-- timeout to elapse, let's just start a new session. The old one will +-- then send its stats before dying. +\c - +SELECT wait_for_hot_stats(); + wait_for_hot_stats +-------------------- + +(1 row) + +SELECT pg_stat_get_tuples_hot_updated('brin_hot'::regclass::oid); + pg_stat_get_tuples_hot_updated +-------------------------------- + 1 +(1 row) + +DROP TABLE brin_hot; +DROP FUNCTION wait_for_hot_stats(); +-- Test handling of index predicates - updating attributes in precicates +-- should not block HOT when summarizing indexes are involved. We update +-- a row that was not indexed due to the index predicate, and becomes +-- indexable - the HOT-updated tuple is forwarded to the BRIN index. +CREATE TABLE brin_hot_2 (a int, b int); +INSERT INTO brin_hot_2 VALUES (1, 100); +CREATE INDEX ON brin_hot_2 USING brin (b) WHERE a = 2; +UPDATE brin_hot_2 SET a = 2; +EXPLAIN (COSTS OFF) SELECT * FROM brin_hot_2 WHERE a = 2 AND b = 100; + QUERY PLAN +----------------------------------- + Seq Scan on brin_hot_2 + Filter: ((a = 2) AND (b = 100)) +(2 rows) + +SELECT COUNT(*) FROM brin_hot_2 WHERE a = 2 AND b = 100; + count +------- + 1 +(1 row) + +SET enable_seqscan = off; +EXPLAIN (COSTS OFF) SELECT * FROM brin_hot_2 WHERE a = 2 AND b = 100; + QUERY PLAN +--------------------------------------------- + Bitmap Heap Scan on brin_hot_2 + Recheck Cond: ((b = 100) AND (a = 2)) + -> Bitmap Index Scan on brin_hot_2_b_idx + Index Cond: (b = 100) +(4 rows) + +SELECT COUNT(*) FROM brin_hot_2 WHERE a = 2 AND b = 100; + count +------- + 1 +(1 row) + +DROP TABLE brin_hot_2; +-- Test that updates to indexed columns are still propagated to the +-- BRIN column. +-- https://postgr.es/m/[email protected] +CREATE TABLE brin_hot_3 (a int, filler text) WITH (fillfactor = 10); +INSERT INTO brin_hot_3 SELECT 1, repeat(' ', 500) FROM generate_series(1, 20); +CREATE INDEX ON brin_hot_3 USING brin (a) WITH (pages_per_range = 1); +UPDATE brin_hot_3 SET a = 2; +EXPLAIN (COSTS OFF) SELECT * FROM brin_hot_3 WHERE a = 2; + QUERY PLAN +--------------------------------------------- + Bitmap Heap Scan on brin_hot_3 + Recheck Cond: (a = 2) + -> Bitmap Index Scan on brin_hot_3_a_idx + Index Cond: (a = 2) +(4 rows) + +SELECT COUNT(*) FROM brin_hot_3 WHERE a = 2; + count +------- + 20 +(1 row) + +DROP TABLE brin_hot_3; +SET enable_seqscan = on; +-- Test that estimation of relation size works with tuples wider than the +-- relation fillfactor. We create a table with wide inline attributes and +-- low fillfactor, insert rows and then see how many rows EXPLAIN shows +-- before running analyze. We disable autovacuum so that it does not +-- interfere with the test. +CREATE TABLE table_fillfactor ( + n char(1000) +) with (fillfactor=10, autovacuum_enabled=off); +INSERT INTO table_fillfactor +SELECT 'x' FROM generate_series(1,1000); +SELECT * FROM check_estimated_rows('SELECT * FROM table_fillfactor'); + estimated | actual +-----------+-------- + 1000 | 1000 +(1 row) + +DROP TABLE table_fillfactor; +-- Test some rewrites +CREATE TABLE test_2pc_timestamp (a int) WITH (autovacuum_enabled = false); +VACUUM ANALYZE test_2pc_timestamp; +SELECT last_analyze AS last_vacuum_analyze FROM pg_stat_all_tables WHERE relname = 'test_2pc_timestamp' \gset +BEGIN; +ALTER TABLE test_2pc_timestamp ALTER COLUMN a TYPE int; +PREPARE TRANSACTION 'test'; +ERROR: prepared transactions are disabled +HINT: Set "max_prepared_transactions" to a nonzero value. +COMMIT PREPARED 'test'; +ERROR: prepared transaction with identifier "test" does not exist +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT last_analyze = :'last_vacuum_analyze'::timestamptz FROM pg_stat_all_tables WHERE relname = 'test_2pc_timestamp'; + ?column? +---------- + t +(1 row) + +DROP TABLE test_2pc_timestamp; +CREATE TABLE test_2pc_rewrite_alone (a int); +INSERT INTO test_2pc_rewrite_alone VALUES (1); +BEGIN; +ALTER TABLE test_2pc_rewrite_alone ALTER COLUMN a TYPE bigint; +PREPARE TRANSACTION 'test'; +ERROR: prepared transactions are disabled +HINT: Set "max_prepared_transactions" to a nonzero value. +COMMIT PREPARED 'test'; +ERROR: prepared transaction with identifier "test" does not exist +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_2pc_rewrite_alone'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 1 | 1 | 0 +(1 row) + +DROP TABLE test_2pc_rewrite_alone; +CREATE TABLE test_2pc (a int); +INSERT INTO test_2pc VALUES (1); +BEGIN; +INSERT INTO test_2pc VALUES (1); +INSERT INTO test_2pc VALUES (2); +INSERT INTO test_2pc VALUES (3); +ALTER TABLE test_2pc ALTER COLUMN a TYPE bigint; +PREPARE TRANSACTION 'test'; +ERROR: prepared transactions are disabled +HINT: Set "max_prepared_transactions" to a nonzero value. +COMMIT PREPARED 'test'; +ERROR: prepared transaction with identifier "test" does not exist +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_2pc'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 4 | 1 | 3 +(1 row) + +DROP TABLE test_2pc; +CREATE TABLE test_2pc_multi (a int); +INSERT INTO test_2pc_multi VALUES (1); +BEGIN; +INSERT INTO test_2pc_multi VALUES (1); +INSERT INTO test_2pc_multi VALUES (2); +ALTER TABLE test_2pc_multi ALTER COLUMN a TYPE bigint; +INSERT INTO test_2pc_multi VALUES (3); +INSERT INTO test_2pc_multi VALUES (4); +ALTER TABLE test_2pc_multi ALTER COLUMN a TYPE int; +INSERT INTO test_2pc_multi VALUES (5); +PREPARE TRANSACTION 'test'; +ERROR: prepared transactions are disabled +HINT: Set "max_prepared_transactions" to a nonzero value. +COMMIT PREPARED 'test'; +ERROR: prepared transaction with identifier "test" does not exist +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_2pc_multi'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 6 | 1 | 5 +(1 row) + +DROP TABLE test_2pc_multi; +CREATE TABLE test_2pc_rewrite_alone_abort (a int); +INSERT INTO test_2pc_rewrite_alone_abort VALUES (1); +BEGIN; +ALTER TABLE test_2pc_rewrite_alone_abort ALTER COLUMN a TYPE bigint; +PREPARE TRANSACTION 'test'; +ERROR: prepared transactions are disabled +HINT: Set "max_prepared_transactions" to a nonzero value. +ROLLBACK PREPARED 'test'; +ERROR: prepared transaction with identifier "test" does not exist +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_2pc_rewrite_alone_abort'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 1 | 1 | 0 +(1 row) + +DROP TABLE test_2pc_rewrite_alone_abort; +CREATE TABLE test_2pc_abort (a int); +INSERT INTO test_2pc_abort VALUES (1); +BEGIN; +INSERT INTO test_2pc_abort VALUES (1); +INSERT INTO test_2pc_abort VALUES (2); +ALTER TABLE test_2pc_abort ALTER COLUMN a TYPE bigint; +INSERT INTO test_2pc_abort VALUES (3); +PREPARE TRANSACTION 'test'; +ERROR: prepared transactions are disabled +HINT: Set "max_prepared_transactions" to a nonzero value. +ROLLBACK PREPARED 'test'; +ERROR: prepared transaction with identifier "test" does not exist +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_2pc_abort'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 4 | 1 | 3 +(1 row) + +DROP TABLE test_2pc_abort; +CREATE TABLE test_2pc_savepoint (a int); +INSERT INTO test_2pc_savepoint VALUES (1); +BEGIN; +SAVEPOINT a; +INSERT INTO test_2pc_savepoint VALUES (1); +INSERT INTO test_2pc_savepoint VALUES (2); +ALTER TABLE test_2pc_savepoint ALTER COLUMN a TYPE bigint; +SAVEPOINT b; +INSERT INTO test_2pc_savepoint VALUES (3); +ALTER TABLE test_2pc_savepoint ALTER COLUMN a TYPE int; +SAVEPOINT c; +INSERT INTO test_2pc_savepoint VALUES (4); +INSERT INTO test_2pc_savepoint VALUES (5); +ROLLBACK TO SAVEPOINT b; +PREPARE TRANSACTION 'test'; +ERROR: prepared transactions are disabled +HINT: Set "max_prepared_transactions" to a nonzero value. +COMMIT PREPARED 'test'; +ERROR: prepared transaction with identifier "test" does not exist +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_2pc_savepoint'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 6 | 1 | 5 +(1 row) + +DROP TABLE test_2pc_savepoint; +-- Rewrite without 2PC +CREATE TABLE test_timestamp (a int) WITH (autovacuum_enabled = false); +VACUUM ANALYZE test_timestamp; +SELECT last_analyze AS last_vacuum_analyze FROM pg_stat_all_tables WHERE relname = 'test_timestamp' \gset +ALTER TABLE test_timestamp ALTER COLUMN a TYPE bigint; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT last_analyze = :'last_vacuum_analyze'::timestamptz FROM pg_stat_all_tables WHERE relname = 'test_timestamp'; + ?column? +---------- + t +(1 row) + +DROP TABLE test_timestamp; +CREATE TABLE test_alone (a int); +INSERT INTO test_alone VALUES (1); +BEGIN; +ALTER TABLE test_alone ALTER COLUMN a TYPE bigint; +COMMIT; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_alone'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 1 | 1 | 0 +(1 row) + +DROP TABLE test_alone; +CREATE TABLE test (a int); +INSERT INTO test VALUES (1); +BEGIN; +INSERT INTO test VALUES (1); +INSERT INTO test VALUES (2); +INSERT INTO test VALUES (3); +ALTER TABLE test ALTER COLUMN a TYPE bigint; +COMMIT; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 4 | 4 | 0 +(1 row) + +DROP TABLE test; +CREATE TABLE test_multi (a int); +INSERT INTO test_multi VALUES (1); +BEGIN; +INSERT INTO test_multi VALUES (1); +INSERT INTO test_multi VALUES (2); +ALTER TABLE test_multi ALTER COLUMN a TYPE bigint; +INSERT INTO test_multi VALUES (3); +INSERT INTO test_multi VALUES (4); +ALTER TABLE test_multi ALTER COLUMN a TYPE int; +INSERT INTO test_multi VALUES (5); +COMMIT; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_multi'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 6 | 6 | 0 +(1 row) + +DROP TABLE test_multi; +CREATE TABLE test_rewrite_alone_abort (a int); +INSERT INTO test_rewrite_alone_abort VALUES (1); +BEGIN; +ALTER TABLE test_rewrite_alone_abort ALTER COLUMN a TYPE bigint; +ROLLBACK; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_rewrite_alone_abort'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 1 | 1 | 0 +(1 row) + +DROP TABLE test_rewrite_alone_abort; +CREATE TABLE test_abort (a int); +INSERT INTO test_abort VALUES (1); +BEGIN; +INSERT INTO test_abort VALUES (1); +INSERT INTO test_abort VALUES (2); +ALTER TABLE test_abort ALTER COLUMN a TYPE bigint; +INSERT INTO test_abort VALUES (3); +ROLLBACK; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_abort'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 4 | 1 | 3 +(1 row) + +DROP TABLE test_abort; +CREATE TABLE test_savepoint (a int); +INSERT INTO test_savepoint VALUES (1); +BEGIN; +SAVEPOINT a; +INSERT INTO test_savepoint VALUES (1); +INSERT INTO test_savepoint VALUES (2); +ALTER TABLE test_savepoint ALTER COLUMN a TYPE bigint; +SAVEPOINT b; +INSERT INTO test_savepoint VALUES (3); +ALTER TABLE test_savepoint ALTER COLUMN a TYPE int; +SAVEPOINT c; +INSERT INTO test_savepoint VALUES (4); +INSERT INTO test_savepoint VALUES (5); +ROLLBACK TO SAVEPOINT b; +COMMIT; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_savepoint'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 6 | 3 | 3 +(1 row) + +DROP TABLE test_savepoint; +CREATE TABLE test_tbs (a int); +INSERT INTO test_tbs VALUES (1); +ALTER TABLE test_tbs SET TABLESPACE pg_default; +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_tbs'; + n_tup_ins | n_live_tup | n_dead_tup +-----------+------------+------------ + 1 | 1 | 0 +(1 row) + +DROP TABLE test_tbs; +-- End of Stats Test diff --git a/src/test/regress/sql/stats.sql b/src/test/regress/sql/stats.sql index 8768e0f27fd..4130f9254a5 100644 --- a/src/test/regress/sql/stats.sql +++ b/src/test/regress/sql/stats.sql @@ -944,4 +944,190 @@ SELECT * FROM check_estimated_rows('SELECT * FROM table_fillfactor'); DROP TABLE table_fillfactor; +-- Test some rewrites +CREATE TABLE test_2pc_timestamp (a int) WITH (autovacuum_enabled = false); +VACUUM ANALYZE test_2pc_timestamp; +SELECT last_analyze AS last_vacuum_analyze FROM pg_stat_all_tables WHERE relname = 'test_2pc_timestamp' \gset +BEGIN; +ALTER TABLE test_2pc_timestamp ALTER COLUMN a TYPE int; +PREPARE TRANSACTION 'test'; +COMMIT PREPARED 'test'; +SELECT pg_stat_force_next_flush(); +SELECT last_analyze = :'last_vacuum_analyze'::timestamptz FROM pg_stat_all_tables WHERE relname = 'test_2pc_timestamp'; +DROP TABLE test_2pc_timestamp; + +CREATE TABLE test_2pc_rewrite_alone (a int); +INSERT INTO test_2pc_rewrite_alone VALUES (1); +BEGIN; +ALTER TABLE test_2pc_rewrite_alone ALTER COLUMN a TYPE bigint; +PREPARE TRANSACTION 'test'; +COMMIT PREPARED 'test'; +SELECT pg_stat_force_next_flush(); +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_2pc_rewrite_alone'; +DROP TABLE test_2pc_rewrite_alone; + +CREATE TABLE test_2pc (a int); +INSERT INTO test_2pc VALUES (1); +BEGIN; +INSERT INTO test_2pc VALUES (1); +INSERT INTO test_2pc VALUES (2); +INSERT INTO test_2pc VALUES (3); +ALTER TABLE test_2pc ALTER COLUMN a TYPE bigint; +PREPARE TRANSACTION 'test'; +COMMIT PREPARED 'test'; +SELECT pg_stat_force_next_flush(); +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_2pc'; +DROP TABLE test_2pc; + +CREATE TABLE test_2pc_multi (a int); +INSERT INTO test_2pc_multi VALUES (1); +BEGIN; +INSERT INTO test_2pc_multi VALUES (1); +INSERT INTO test_2pc_multi VALUES (2); +ALTER TABLE test_2pc_multi ALTER COLUMN a TYPE bigint; +INSERT INTO test_2pc_multi VALUES (3); +INSERT INTO test_2pc_multi VALUES (4); +ALTER TABLE test_2pc_multi ALTER COLUMN a TYPE int; +INSERT INTO test_2pc_multi VALUES (5); +PREPARE TRANSACTION 'test'; +COMMIT PREPARED 'test'; +SELECT pg_stat_force_next_flush(); +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_2pc_multi'; +DROP TABLE test_2pc_multi; + +CREATE TABLE test_2pc_rewrite_alone_abort (a int); +INSERT INTO test_2pc_rewrite_alone_abort VALUES (1); +BEGIN; +ALTER TABLE test_2pc_rewrite_alone_abort ALTER COLUMN a TYPE bigint; +PREPARE TRANSACTION 'test'; +ROLLBACK PREPARED 'test'; +SELECT pg_stat_force_next_flush(); +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_2pc_rewrite_alone_abort'; +DROP TABLE test_2pc_rewrite_alone_abort; + +CREATE TABLE test_2pc_abort (a int); +INSERT INTO test_2pc_abort VALUES (1); +BEGIN; +INSERT INTO test_2pc_abort VALUES (1); +INSERT INTO test_2pc_abort VALUES (2); +ALTER TABLE test_2pc_abort ALTER COLUMN a TYPE bigint; +INSERT INTO test_2pc_abort VALUES (3); +PREPARE TRANSACTION 'test'; +ROLLBACK PREPARED 'test'; +SELECT pg_stat_force_next_flush(); +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_2pc_abort'; +DROP TABLE test_2pc_abort; + +CREATE TABLE test_2pc_savepoint (a int); +INSERT INTO test_2pc_savepoint VALUES (1); +BEGIN; +SAVEPOINT a; +INSERT INTO test_2pc_savepoint VALUES (1); +INSERT INTO test_2pc_savepoint VALUES (2); +ALTER TABLE test_2pc_savepoint ALTER COLUMN a TYPE bigint; +SAVEPOINT b; +INSERT INTO test_2pc_savepoint VALUES (3); +ALTER TABLE test_2pc_savepoint ALTER COLUMN a TYPE int; +SAVEPOINT c; +INSERT INTO test_2pc_savepoint VALUES (4); +INSERT INTO test_2pc_savepoint VALUES (5); +ROLLBACK TO SAVEPOINT b; +PREPARE TRANSACTION 'test'; +COMMIT PREPARED 'test'; +SELECT pg_stat_force_next_flush(); +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_2pc_savepoint'; +DROP TABLE test_2pc_savepoint; + +-- Rewrite without 2PC +CREATE TABLE test_timestamp (a int) WITH (autovacuum_enabled = false); +VACUUM ANALYZE test_timestamp; +SELECT last_analyze AS last_vacuum_analyze FROM pg_stat_all_tables WHERE relname = 'test_timestamp' \gset +ALTER TABLE test_timestamp ALTER COLUMN a TYPE bigint; +SELECT pg_stat_force_next_flush(); +SELECT last_analyze = :'last_vacuum_analyze'::timestamptz FROM pg_stat_all_tables WHERE relname = 'test_timestamp'; +DROP TABLE test_timestamp; + +CREATE TABLE test_alone (a int); +INSERT INTO test_alone VALUES (1); +BEGIN; +ALTER TABLE test_alone ALTER COLUMN a TYPE bigint; +COMMIT; +SELECT pg_stat_force_next_flush(); +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_alone'; +DROP TABLE test_alone; + +CREATE TABLE test (a int); +INSERT INTO test VALUES (1); +BEGIN; +INSERT INTO test VALUES (1); +INSERT INTO test VALUES (2); +INSERT INTO test VALUES (3); +ALTER TABLE test ALTER COLUMN a TYPE bigint; +COMMIT; +SELECT pg_stat_force_next_flush(); +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test'; +DROP TABLE test; + +CREATE TABLE test_multi (a int); +INSERT INTO test_multi VALUES (1); +BEGIN; +INSERT INTO test_multi VALUES (1); +INSERT INTO test_multi VALUES (2); +ALTER TABLE test_multi ALTER COLUMN a TYPE bigint; +INSERT INTO test_multi VALUES (3); +INSERT INTO test_multi VALUES (4); +ALTER TABLE test_multi ALTER COLUMN a TYPE int; +INSERT INTO test_multi VALUES (5); +COMMIT; +SELECT pg_stat_force_next_flush(); +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_multi'; +DROP TABLE test_multi; + +CREATE TABLE test_rewrite_alone_abort (a int); +INSERT INTO test_rewrite_alone_abort VALUES (1); +BEGIN; +ALTER TABLE test_rewrite_alone_abort ALTER COLUMN a TYPE bigint; +ROLLBACK; +SELECT pg_stat_force_next_flush(); +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_rewrite_alone_abort'; +DROP TABLE test_rewrite_alone_abort; + +CREATE TABLE test_abort (a int); +INSERT INTO test_abort VALUES (1); +BEGIN; +INSERT INTO test_abort VALUES (1); +INSERT INTO test_abort VALUES (2); +ALTER TABLE test_abort ALTER COLUMN a TYPE bigint; +INSERT INTO test_abort VALUES (3); +ROLLBACK; +SELECT pg_stat_force_next_flush(); +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_abort'; +DROP TABLE test_abort; + +CREATE TABLE test_savepoint (a int); +INSERT INTO test_savepoint VALUES (1); +BEGIN; +SAVEPOINT a; +INSERT INTO test_savepoint VALUES (1); +INSERT INTO test_savepoint VALUES (2); +ALTER TABLE test_savepoint ALTER COLUMN a TYPE bigint; +SAVEPOINT b; +INSERT INTO test_savepoint VALUES (3); +ALTER TABLE test_savepoint ALTER COLUMN a TYPE int; +SAVEPOINT c; +INSERT INTO test_savepoint VALUES (4); +INSERT INTO test_savepoint VALUES (5); +ROLLBACK TO SAVEPOINT b; +COMMIT; +SELECT pg_stat_force_next_flush(); +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_savepoint'; +DROP TABLE test_savepoint; + +CREATE TABLE test_tbs (a int); +INSERT INTO test_tbs VALUES (1); +ALTER TABLE test_tbs SET TABLESPACE pg_default; +SELECT pg_stat_force_next_flush(); +SELECT n_tup_ins, n_live_tup, n_dead_tup FROM pg_stat_all_tables WHERE relname = 'test_tbs'; +DROP TABLE test_tbs; + -- End of Stats Test -- 2.34.1 --KMYjwlsACqdYx2P8 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v7-0002-Key-PGSTAT_KIND_RELATION-by-relfile-locator.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 261+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 261+ messages in thread
end of thread, other threads:[~2026-03-11 14:19 UTC | newest] Thread overview: 261+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2022-07-02 05:48 [PATCH] fix "Preserve relfilenodes" for pg_largeobject and its index Justin Pryzby <[email protected]> 2025-10-27 14:54 [PATCH v7 1/3] Add stats tests related to rewrite Bertrand Drouvot <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox